SU\G(𝔸)/K·U
Sign Up for free Log In

Author Description

Login to generate an author description

Ask a Question About This Mathematician

nuScenes: A Multimodal Dataset for Autonomous Driving

2020-06-01
Holger Caesar , Varun Bankiti , Alex Lang +7 more
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, … Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
View PDF Chat

PointPillars: Fast Encoders for Object Detection From Point Clouds

2019-06-01
Alex Lang , Sourabh Vora , Holger Caesar +3 more
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into … Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work, we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2018-06-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff1, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.
View PDF Chat

Panoptic Nuscenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

2022-02-07
Whye Kit Fong , Rohit Mohan , Juana Valeria Hurtado +4 more
Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, … Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, performing these tasks using LiDAR point clouds provides reliable predictions. However, existing datasets lack diversity in the type of urban scenes and have a limited number of dynamic object instances which hinders both learning of these tasks as well as credible benchmarking of the developed methods. In this letter, we introduce the large-scale Panoptic nuScenes benchmark dataset that extends our popular nuScenes dataset with point-wise groundtruth annotations for semantic segmentation, panoptic segmentation, and panoptic tracking tasks. To facilitate comparison, we provide several strong baselines for each of these tasks on our proposed dataset. Moreover, we analyze the drawbacks of the existing metrics for panoptic tracking and propose the novel instance-centric PAT metric that addresses the concerns. We present exhaustive experiments that demonstrate the utility of Panoptic nuScenes compared to existing datasets and make the online evaluation server available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nuScenes.org</uri> . We believe that this extension will accelerate the research of novel methods for scene understanding of dynamic urban environments.
View PDF Chat

Weakly Supervised Object Localization Using Things and Stuff Transfer

2017-10-01
Miaojing Shi , Holger Caesar , Vittorio Ferrari
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The … We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this, we acquire three types of knowledge from the source set: a segmentation model trained on both thing and stuff classes; similarity relations between target and source classes; and cooccurrence relations between thing and stuff classes in the source. The segmentation model is used to generate thing and stuff segmentation maps on a target image, while the class similarity and co-occurrence knowledge help refining them. We then incorporate these maps as new cues into a multiple instance learning framework (MIL), propagating the transferred knowledge from the pixel level to the object proposal level. In extensive experiments, we conduct our transfer from the PASCAL Context dataset (source) to the ILSVRC, COCO and PASCAL VOC 2007 datasets (targets). We evaluate our transfer across widely different thing classes, including some that are not similar in appearance, but appear against similar background. The results demonstrate significant improvement over standard MIL, and we outperform the state-of-the-art in the transfer setting.
View PDF Chat

Region-Based Semantic Segmentation with End-to-End Training

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
View PDF Chat

NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

2021-01-01
Holger Caesar , Juraj Kabzan , Kok Seang Tan +6 more
In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets … In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-scale driving dataset, lightweight closed-loop simulator, and motion-planning-specific metrics. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics. We plan to release the dataset at NeurIPS 2021 and organize benchmark challenges starting in early 2022.
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2016-12-12
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.

Joint Calibration for Semantic Segmentation

2015-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels … Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels in the training images. In the weakly supervised setting, class-labels are only given at the image-level. We tackle both settings in a single framework which builds on region-based classification. Our framework addresses three problems common to region-based semantic segmentation. First of all, objects naturally occur at different scales within an image [3]. Performing recognition at a single scale inevitably leads to regions covering only parts of an object which may have ambiguous appearance, and to regions straddling over multiple objects, whose classification is harder due to their mixed appearance. Therefore many recent methods operate on pools of regions computed at multiple scales, which have a much better chance of containing some regions covering complete objects [1, 2]. However, this leads to overlapping regions which may lead to conflicting class predictions at the pixel-level. These conflicts need to be properly resolved. Secondly, classes are often unbalanced [2, 4]: “cars” and “grass” are frequently found in images while “tricycles” and “gravel” are much rarer. Due to the nature of most classifiers, without careful consideration these rare classes are largely ignored: even if the class occurs in an image the system will rarely predict it. Since class-frequencies typically follow a power-law distribution, this problem becomes increasingly important with the modern trend towards larger datasets with more and more classes. Finally, classes compete: a pixel can only be assigned to a single class (e.g. it can not belong to both “sky” and “airplane”). To properly resolve such competition, a semantic segmentation framework should take into account predictions for multiple classes jointly. In this paper we address these three problems with a joint calibration method over a set of SVMs. Model. We represent an image by a set of overlapping regions [3] described by CNN features [1]. Our semantic segmentation model infers the label op of each pixel p in an image:
View PDF Chat

nuScenes: A multimodal dataset for autonomous driving

2019-01-01
Holger Caesar , Varun Bankiti , Alex Lang +7 more
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, … Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
View PDF Chat

SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation

2023-06-01
Ted Lentsch , Zimin Xia , Holger Caesar +1 more
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which … This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view attention module for ground-view guided aerial feature selection and utilizes the geometric projection of the ground camera's viewing frustum on the aerial image to pool features. The efficient construction of aerial descriptors is achieved using precomputed masks. SliceMatch is trained using contrastive learning and pose estimation is formulated as a similarity comparison between the ground descriptor and the aerial descriptors. Compared to the state-of-the-art, SliceMatch achieves a 19% lower median localization error on the VIGOR benchmark using the same VGG16 backbone at 150 frames per second, and a 50% lower error when using a ResNet50 backbone.
View PDF Chat

Weakly Supervised Object Localization Using Things and Stuff Transfer

2017-01-01
Miaojing Shi , Holger Caesar , Vittorio Ferrari
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The … We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this, we acquire three types of knowledge from the source set: a segmentation model trained on both thing and stuff classes; similarity relations between target and source classes; and co-occurrence relations between thing and stuff classes in the source. The segmentation model is used to generate thing and stuff segmentation maps on a target image, while the class similarity and co-occurrence knowledge help refining them. We then incorporate these maps as new cues into a multiple instance learning framework (MIL), propagating the transferred knowledge from the pixel level to the object proposal level. In extensive experiments, we conduct our transfer from the PASCAL Context dataset (source) to the ILSVRC, COCO and PASCAL VOC 2007 datasets (targets). We evaluate our transfer across widely different thing classes, including some that are not similar in appearance, but appear against similar background. The results demonstrate significant improvement over standard MIL, and we outperform the state-of-the-art in the transfer setting.
View PDF Chat

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

2023-10-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to … Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods. Code is available at https://github.com/franciszzj/HiLo.
View PDF Chat

PointPillars: Fast Encoders for Object Detection from Point Clouds

2018-01-01
Alex Lang , Sourabh Vora , Holger Caesar +3 more
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into … Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
View PDF Chat

The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes

2020-01-01
Yiluan Guo , Holger Caesar , Oscar Beijbom +2 more
A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and … A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and distance of the actors in the scene, which are important for the safe AD. It also ignores environmental context. Recently, Philion et al. proposed a neural planning metric (PKL), based on the KL divergence of a planner's trajectory and the groundtruth route, to accommodate these requirements. In this paper, we use this neural planning metric to score all submissions of the nuScenes detection challenge and analyze the results. We find that while somewhat correlated with mAP, the PKL metric shows different behavior to increased traffic density, ego velocity, road curvature and intersections. Finally, we propose ideas to extend the neural planning metric.

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

2024-06-02
Shiming Wang , Holger Caesar , Liangliang Nan +1 more
View PDF Chat

Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving

2024-05-13
Napat Karnchanachari , Dimitris Geromichalos , Kok Seang Tan +7 more
View PDF Chat

Joint Calibration for Semantic Segmentation

2015-07-06
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and … Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3) Each pixel can only be assigned to a single class, which creates competition between classes. We address all three problems with a joint calibration method which optimizes a multi-class loss defined over the final pixel-level output labeling, as opposed to simply region classification. Our method outperforms the state-of-the-art on the popular SIFT Flow [18] dataset in both the fully and weakly supervised setting by a considerably margin (+6% and +10%, respectively).

nuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles.

2021-06-22
Holger Caesar , Juraj Kabzan , Kok Seang Tan +6 more
In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets … In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-scale driving dataset, lightweight closed-loop simulator, and motion-planning-specific metrics. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics. We plan to release the dataset at NeurIPS 2021 and organize benchmark challenges starting in early 2022.

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

2021-01-01
Whye Kit Fong , Rohit Mohan , Juana Valeria Hurtado +4 more
Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, … Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, performing these tasks using LiDAR point clouds provides reliable predictions. However, existing datasets lack diversity in the type of urban scenes and have a limited number of dynamic object instances which hinders both learning of these tasks as well as credible benchmarking of the developed methods. In this paper, we introduce the large-scale Panoptic nuScenes benchmark dataset that extends our popular nuScenes dataset with point-wise groundtruth annotations for semantic segmentation, panoptic segmentation, and panoptic tracking tasks. To facilitate comparison, we provide several strong baselines for each of these tasks on our proposed dataset. Moreover, we analyze the drawbacks of the existing metrics for panoptic tracking and propose the novel instance-centric PAT metric that addresses the concerns. We present exhaustive experiments that demonstrate the utility of Panoptic nuScenes compared to existing datasets and make the online evaluation server available at nuScenes.org. We believe that this extension will accelerate the research of novel methods for scene understanding of dynamic urban environments.

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

2023-01-01
Shiming Wang , Holger Caesar , Liangliang Nan +1 more
Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor … Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor failure, is a critical problem which remains under-studied. In this work, we propose UniBEV, an end-to-end multi-modal 3D object detection framework designed for robustness against missing modalities: UniBEV can operate on LiDAR plus camera input, but also on LiDAR-only or camera-only input without retraining. To facilitate its detector head to handle different input combinations, UniBEV aims to create well-aligned Bird's Eye View (BEV) feature maps from each available modality. Unlike prior BEV-based multi-modal detection methods, all sensor modalities follow a uniform approach to resample features from the native sensor coordinate systems to the BEV features. We furthermore investigate the robustness of various fusion strategies w.r.t. missing modalities: the commonly used feature concatenation, but also channel-wise averaging, and a generalization to weighted averaging termed Channel Normalized Weights. To validate its effectiveness, we compare UniBEV to state-of-the-art BEVFusion and MetaBEV on nuScenes over all sensor input combinations. In this setting, UniBEV achieves $52.5 \%$ mAP on average over all input combinations, significantly improving over the baselines ($43.5 \%$ mAP on average for BEVFusion, $48.7 \%$ mAP on average for MetaBEV). An ablation study shows the robustness benefits of fusing by weighted averaging over regular concatenation, and of sharing queries between the BEV encoders of each modality. Our code will be released upon paper acceptance.

VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation

2023-01-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations leads to unsatisfactory … Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations leads to unsatisfactory results in real-world applications. Prior methods predominantly rely on vision information or utilize limited language information, such as object or relation names, thereby overlooking the utility of language information. Leveraging the recent progress in Large Language Models (LLMs), we propose to use language information to assist relation prediction, particularly for rare relations. To this end, we propose the Vision-Language Prompting (VLPrompt) model, which acquires vision information from images and language information from LLMs. Then, through a prompter network based on attention mechanism, it achieves precise relation prediction. Our extensive experiments show that VLPrompt significantly outperforms previous state-of-the-art methods on the PSG dataset, proving the effectiveness of incorporating language information and alleviating the long-tail problem of relations.
View PDF Chat

BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

2024-05-13
Jiarong Wei , Yancong Lin , Holger Caesar
View PDF Chat

Region-based semantic segmentation with end-to-end training

2016-07-26
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main … We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0% on SIFT Flow and 49.9% on PASCAL Context, and is particularly accurate at object boundaries.

Joint Calibration for Semantic Segmentation

2015-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and … Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3) Each pixel can only be assigned to a single class, which creates competition between classes. We address all three problems with a joint calibration method which optimizes a multi-class loss defined over the final pixel-level output labeling, as opposed to simply region classification. Our method outperforms the state-of-the-art on the popular SIFT Flow [18] dataset in both the fully and weakly supervised setting by a considerably margin (+6% and +10%, respectively).
View PDF Chat

Region-based semantic segmentation with end-to-end training

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main … We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0% on SIFT Flow and 49.9% on PASCAL Context, and is particularly accurate at object boundaries.
View PDF Chat

SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

2022-01-01
Ted Lentsch , Zimin Xia , Holger Caesar +1 more
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which … This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view attention module for ground-view guided aerial feature selection and utilizes the geometric projection of the ground camera's viewing frustum on the aerial image to pool features. The efficient construction of aerial descriptors is achieved using precomputed masks. SliceMatch is trained using contrastive learning and pose estimation is formulated as a similarity comparison between the ground descriptor and the aerial descriptors. Compared to the state-of-the-art, SliceMatch achieves a 19% lower median localization error on the VIGOR benchmark using the same VGG16 backbone at 150 frames per second, and a 50% lower error when using a ResNet50 backbone.
View PDF Chat

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

2023-01-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to … Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods. Code is available at https://github.com/franciszzj/HiLo.
View PDF Chat

Offline Tracking with Object Permanence

2023-01-01
Xianzhong Liu , Holger Caesar
To reduce the expensive labor cost for manual labeling autonomous driving datasets, an alternative is to automatically label the datasets using an offline perception system. However, objects might be temporally … To reduce the expensive labor cost for manual labeling autonomous driving datasets, an alternative is to automatically label the datasets using an offline perception system. However, objects might be temporally occluded. Such occlusion scenarios in the datasets are common yet underexplored in offline auto labeling. In this work, we propose an offline tracking model that focuses on occluded object tracks. It leverages the concept of object permanence which means objects continue to exist even if they are not observed anymore. The model contains three parts: a standard online tracker, a re-identification (Re-ID) module that associates tracklets before and after occlusion, and a track completion module that completes the fragmented tracks. The Re-ID module and the track completion module use the vectorized map as one of the inputs to refine the tracking results with occlusion. The model can effectively recover the occluded object trajectories. It achieves state-of-the-art performance in 3D multi-object tracking by significantly improving the original online tracking result, showing its potential to be applied in offline auto labeling as a useful plugin to improve tracking by recovering occlusions.
View PDF Chat

BaSAL: Size Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

2023-01-01
Jiarong Wei , Yancong Lin , Holger Caesar
Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then … Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then training a model from these samples. We identify two problems with existing active learning methods for LiDAR semantic segmentation. First, they overlook the severe class imbalance inherent in LiDAR semantic segmentation datasets. Second, to bootstrap the active learning loop when there is no labeled data available, they train their initial model from randomly selected data samples, leading to low performance. This situation is referred to as the cold start problem. To address these problems we propose BaSAL, a size-balanced warm start active learning model, based on the observation that each object class has a characteristic size. By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced. Furthermore, in contrast to existing information measures like entropy or CoreSet, size-based sampling does not require a pretrained model, thus addressing the cold start problem effectively. Results show that we are able to improve the performance of the initial model by a large margin. Combining warm start and size-balanced sampling with established information measures, our approach achieves comparable performance to training on the entire SemanticKITTI dataset, despite using only 5% of the annotations, outperforming existing active learning methods. We also match the existing state-of-the-art in active learning on nuScenes. Our code is available at: https://github.com/Tony-WJR/BaSAL.

Graph Convolutional Networks for Complex Traffic Scenario Classification

2023-01-01
Tobias Hoek , Holger Caesar , Andreas Falkovén +1 more
A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems (ADS). Identifying these scenarios in an automated manner is … A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems (ADS). Identifying these scenarios in an automated manner is a challenging task. Most methods on scenario classification do not work for complex scenarios with diverse environments (highways, urban) and interaction with other traffic agents. This is mirrored in their approaches which model an individual vehicle in relation to its environment, but neglect the interaction between multiple vehicles (e.g. cut-ins, stationary lead vehicle). Furthermore, existing datasets lack diversity and do not have per-frame annotations to accurately learn the start and end time of a scenario. We propose a method for complex traffic scenario classification that is able to model the interaction of a vehicle with the environment, as well as other agents. We use Graph Convolutional Networks to model spatial and temporal aspects of these scenarios. Expanding the nuScenes and Argoverse 2 driving datasets, we introduce a scenario-labeled dataset, which covers different driving environments and is annotated per frame. Training our method on this dataset, we present a promising baseline for future research on per-frame complex scenario classification.

ICP-Flow: LiDAR Scene Flow Estimation with ICP

2024-02-27
Yancong Lin , Holger Caesar
Scene flow characterizes the 3D motion between two LiDAR scans captured by an autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point-wise unconstrained flow vectors that can … Scene flow characterizes the 3D motion between two LiDAR scans captured by an autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point-wise unconstrained flow vectors that can be learned by either large-scale training beforehand or time-consuming optimization at inference. However, these methods do not take into account that objects in autonomous driving often move rigidly. We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations. We propose ICP-Flow, a learning-free flow estimator. The core of our design is the conventional Iterative Closest Point (ICP) algorithm, which aligns the objects over time and outputs the corresponding rigid transformations. Crucially, to aid ICP, we propose a histogram-based initialization that discovers the most likely translation, thus providing a good starting point for ICP. The complete scene flow is then recovered from the rigid transformations. We outperform state-of-the-art baselines, including supervised models, on the Waymo dataset and perform competitively on Argoverse-v2 and nuScenes. Further, we train a feedforward neural network, supervised by the pseudo labels from our model, and achieve top performance among all models capable of real-time inference. We validate the advantage of our model on scene flow estimation with longer temporal gaps, up to 0.5 seconds where other models fail to deliver meaningful results.
View PDF Chat

Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving

2024-03-06
Napat Karnchanachari , Dimitris Geromichalos , Kok Seang Tan +7 more
Machine Learning (ML) has replaced traditional handcrafted methods for perception and prediction in autonomous vehicles. Yet for the equally important planning task, the adoption of ML-based techniques is slow. We … Machine Learning (ML) has replaced traditional handcrafted methods for perception and prediction in autonomous vehicles. Yet for the equally important planning task, the adoption of ML-based techniques is slow. We present nuPlan, the world's first real-world autonomous driving dataset, and benchmark. The benchmark is designed to test the ability of ML-based planners to handle diverse driving situations and to make safe and efficient decisions. To that end, we introduce a new large-scale dataset that consists of 1282 hours of diverse driving scenarios from 4 cities (Las Vegas, Boston, Pittsburgh, and Singapore) and includes high-quality auto-labeled object tracks and traffic light data. We exhaustively mine and taxonomize common and rare driving scenarios which are used during evaluation to get fine-grained insights into the performance and characteristics of a planner. Beyond the dataset, we provide a simulation and evaluation framework that enables a planner's actions to be simulated in closed-loop to account for interactions with other traffic participants. We present a detailed analysis of numerous baselines and investigate gaps between ML-based and traditional methods. Find the nuPlan dataset and code at nuplan.org.
View PDF Chat

DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection

2024-04-03
Felix Fent , Andras Palffy , Holger Caesar
The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based … The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based perception is still inferior to the others. Camera-radar fusion methods have been proposed to address this issue, but these are constrained by the typical sparsity of radar point clouds and often designed for radars without elevation information. We propose a novel camera-radar fusion approach called Dual Perspective Fusion Transformer (DPFT), designed to overcome these limitations. Our method leverages lower-level radar data (the radar cube) instead of the processed point clouds to preserve as much information as possible and employs projections in both the camera and ground planes to effectively use radars with elevation information and simplify the fusion with camera data. As a result, DPFT has demonstrated state-of-the-art performance on the K-Radar dataset while showing remarkable robustness against adverse weather conditions and maintaining a low inference time. The code is made available as open-source software under https://github.com/TUMFTM/DPFT.
View PDF Chat

Label-Efficient 3D Object Detection For Road-Side Units

2024-06-02
Minh-Quan Dao , Holger Caesar , Julie Stephany Berrío +4 more
Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of … Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU), thus minimizing the impact of occlusion. While significant advancement has been made, the data-hungry nature of these methods creates a major hurdle for their real-world deployment, particularly due to the need for annotated RSU data. Manually annotating the vast amount of RSU data required for training is prohibitively expensive, given the sheer number of intersections and the effort involved in annotating point clouds. We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery. Our paper introduces two new modules: one for object discovery based on a spatial-temporal aggregation of point clouds, and another for refinement. Furthermore, we demonstrate that fine-tuning on a small portion of annotated data allows our object discovery models to narrow the performance gap with, or even surpass, fully supervised models. Extensive experiments are carried out in simulated and real-world datasets to evaluate our method.
View PDF Chat

UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes

2024-05-24
Ted Lentsch , Holger Caesar , Dariu M. Gavrila
Unsupervised 3D object detection methods have emerged to leverage vast amounts of data efficiently without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect … Unsupervised 3D object detection methods have emerged to leverage vast amounts of data efficiently without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect objects but penalize the detections of static instances during training. Multiple rounds of (self) training are used in which detected static instances are added to the set of training targets; this procedure to improve performance is computationally expensive. To address this, we propose the method UNION. We use spatial clustering and self-supervised scene flow to obtain a set of static and dynamic object proposals from LiDAR. Subsequently, object proposals' visual appearances are encoded to distinguish static objects in the foreground and background by selecting static instances that are visually similar to dynamic objects. As a result, static and dynamic foreground objects are obtained together, and existing detectors can be trained with a single training. In addition, we extend 3D object discovery to detection by using object appearance-based cluster labels as pseudo-class labels for training object classification. We conduct extensive experiments on the nuScenes dataset and increase the state-of-the-art performance for unsupervised object discovery, i.e. UNION more than doubles the average precision to 33.9. The code will be made publicly available.
View PDF Chat

Redefining Automotive Radar Imaging: A Domain-Informed 1D Deep Learning Approach for High-Resolution and Efficient Performance

2024-06-11
Ruxin Zheng , Shunqiao Sun , Holger Caesar +2 more
Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for … Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for precise semantic scene interpretation. Classical super-resolution techniques adapted from optical imaging inadequately address the distinct characteristics of radar signal data. In response, our study redefines radar imaging super-resolution as a one-dimensional (1D) signal super-resolution spectra estimation problem by harnessing the radar signal processing domain knowledge, introducing innovative data normalization and a domain-informed signal-to-noise ratio (SNR)-guided loss function. Our tailored deep learning network for automotive radar imaging exhibits remarkable scalability, parameter efficiency and fast inference speed, alongside enhanced performance in terms of radar imaging quality and resolution. Extensive testing confirms that our SR-SPECNet sets a new benchmark in producing high-resolution radar range-azimuth images, outperforming existing methods across varied antenna configurations and dataset sizes. Source code and new radar dataset will be made publicly available online.
View PDF Chat

Offline Tracking with Object Permanence

2024-06-02
Xianzhong Liu , Holger Caesar
View PDF Chat

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

2024-07-15
Zijian Zhou , Zheng Zhu , Holger Caesar +1 more
Panoptic Scene Graph Generation (PSG) aims to segment objects and recognize their relations, enabling the structured understanding of an image. Previous methods focus on predicting predefined object and relation categories, … Panoptic Scene Graph Generation (PSG) aims to segment objects and recognize their relations, enabling the structured understanding of an image. Previous methods focus on predicting predefined object and relation categories, hence limiting their applications in the open world scenarios. With the rapid development of large multimodal models (LMMs), significant progress has been made in open-set object detection and segmentation, yet open-set relation prediction in PSG remains unexplored. In this paper, we focus on the task of open-set relation prediction integrated with a pretrained open-set panoptic segmentation model to achieve true open-set panoptic scene graph generation (OpenPSG). Our OpenPSG leverages LMMs to achieve open-set relation prediction in an autoregressive manner. We introduce a relation query transformer to efficiently extract visual features of object pairs and estimate the existence of relations between them. The latter can enhance the prediction efficiency by filtering irrelevant pairs. Finally, we design the generation and judgement instructions to perform open-set relation prediction in PSG autoregressively. To our knowledge, we are the first to propose the open-set PSG task. Extensive experiments demonstrate that our method achieves state-of-the-art performance in open-set relation prediction and panoptic scene graph generation. Code is available at \url{https://github.com/franciszzj/OpenPSG}.
View PDF Chat

OSSA: Unsupervised One-Shot Style Adaptation

2024-10-01
Robin Gerster , Holger Caesar , Matthias Rapp +2 more
Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, … Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, we introduce One-Shot Style Adaptation (OSSA), a novel unsupervised domain adaptation method for object detection that utilizes a single, unlabeled target image to approximate the target domain style. Specifically, OSSA generates diverse target styles by perturbing the style statistics derived from a single target image and then applies these styles to a labeled source dataset at the feature level using Adaptive Instance Normalization (AdaIN). Extensive experiments show that OSSA establishes a new state-of-the-art among one-shot domain adaptation methods by a significant margin, and in some cases, even outperforms strong baselines that use thousands of unlabeled target images. By applying OSSA in various scenarios, including weather, simulated-to-real (sim2real), and visual-to-thermal adaptations, our study explores the overarching significance of the style gap in these contexts. OSSA's simplicity and efficiency allow easy integration into existing frameworks, providing a potentially viable solution for practical applications with limited data availability. Code is available at https://github.com/RobinGerster7/OSSA
View PDF Chat

Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving

2024-06-24
Karim Armanious , Maurice Quach , Michaël Ulrich +7 more
This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD … This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD offers a unique integration of high-resolution imaging radar, lidar, and camera sensors, providing unprecedented 360-degree coverage to bridge the current gap in high-resolution radar data availability. Spanning urban, rural, and highway environments, BSD enables detailed exploration into radar-based object detection and sensor fusion techniques. The dataset is aimed at facilitating academic and research collaborations between Bosch and current and future partners. This aims to foster joint efforts in developing cutting-edge HAD and ADAS technologies. The paper describes the dataset's key attributes, including its scalability, radar resolution, and labeling methodology. Key offerings also include initial benchmarks for sensor modalities and a development kit tailored for extensive data analysis and performance evaluation, underscoring our commitment to contributing valuable resources to the HAD and ADAS research community.
View PDF Chat

LeAP: Consistent multi-domain 3D labeling using Foundation Models

2025-02-06
Simon Gebraad , Andras Palffy , Holger Caesar
Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled 3D point cloud data is straightforward, manually annotating this data with semantic labels … Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled 3D point cloud data is straightforward, manually annotating this data with semantic labels is time-consuming and costly. Recently, Vision Foundation Models (VFMs) enable open-set semantic segmentation on camera images, potentially aiding automatic labeling. However,VFMs for 3D data have been limited to adaptations of 2D models, which can introduce inconsistencies to 3D labels. This work introduces Label Any Pointcloud (LeAP), leveraging 2D VFMs to automatically label 3D data with any set of classes in any kind of application whilst ensuring label consistency. Using a Bayesian update, point labels are combined into voxels to improve spatio-temporal consistency. A novel 3D Consistency Network (3D-CN) exploits 3D information to further improve label quality. Through various experiments, we show that our method can generate high-quality 3D semantic labels across diverse fields without any manual labeling. Further, models adapted to new domains using our labels show up to a 34.2 mIoU increase in semantic segmentation tasks.
View PDF Chat

OSSA: Unsupervised One-Shot Style Adaptation

2025-01-01
Robin Gerster , Holger Caesar , Matthias Rapp +2 more

LeAP: Consistent multi-domain 3D labeling using Foundation Models

2025-02-06
Simon Gebraad , Andras Palffy , Holger Caesar
Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled 3D point cloud data is straightforward, manually annotating this data with semantic labels … Availability of datasets is a strong driver for research on 3D semantic understanding, and whilst obtaining unlabeled 3D point cloud data is straightforward, manually annotating this data with semantic labels is time-consuming and costly. Recently, Vision Foundation Models (VFMs) enable open-set semantic segmentation on camera images, potentially aiding automatic labeling. However,VFMs for 3D data have been limited to adaptations of 2D models, which can introduce inconsistencies to 3D labels. This work introduces Label Any Pointcloud (LeAP), leveraging 2D VFMs to automatically label 3D data with any set of classes in any kind of application whilst ensuring label consistency. Using a Bayesian update, point labels are combined into voxels to improve spatio-temporal consistency. A novel 3D Consistency Network (3D-CN) exploits 3D information to further improve label quality. Through various experiments, we show that our method can generate high-quality 3D semantic labels across diverse fields without any manual labeling. Further, models adapted to new domains using our labels show up to a 34.2 mIoU increase in semantic segmentation tasks.
View PDF Chat

OSSA: Unsupervised One-Shot Style Adaptation

2025-01-01
Robin Gerster , Holger Caesar , Matthias Rapp +2 more

OSSA: Unsupervised One-Shot Style Adaptation

2024-10-01
Robin Gerster , Holger Caesar , Matthias Rapp +2 more
Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, … Despite their success in various vision tasks, deep neural network architectures often underperform in out-of-distribution scenarios due to the difference between training and target domain style. To address this limitation, we introduce One-Shot Style Adaptation (OSSA), a novel unsupervised domain adaptation method for object detection that utilizes a single, unlabeled target image to approximate the target domain style. Specifically, OSSA generates diverse target styles by perturbing the style statistics derived from a single target image and then applies these styles to a labeled source dataset at the feature level using Adaptive Instance Normalization (AdaIN). Extensive experiments show that OSSA establishes a new state-of-the-art among one-shot domain adaptation methods by a significant margin, and in some cases, even outperforms strong baselines that use thousands of unlabeled target images. By applying OSSA in various scenarios, including weather, simulated-to-real (sim2real), and visual-to-thermal adaptations, our study explores the overarching significance of the style gap in these contexts. OSSA's simplicity and efficiency allow easy integration into existing frameworks, providing a potentially viable solution for practical applications with limited data availability. Code is available at https://github.com/RobinGerster7/OSSA
View PDF Chat

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models

2024-07-15
Zijian Zhou , Zheng Zhu , Holger Caesar +1 more
Panoptic Scene Graph Generation (PSG) aims to segment objects and recognize their relations, enabling the structured understanding of an image. Previous methods focus on predicting predefined object and relation categories, … Panoptic Scene Graph Generation (PSG) aims to segment objects and recognize their relations, enabling the structured understanding of an image. Previous methods focus on predicting predefined object and relation categories, hence limiting their applications in the open world scenarios. With the rapid development of large multimodal models (LMMs), significant progress has been made in open-set object detection and segmentation, yet open-set relation prediction in PSG remains unexplored. In this paper, we focus on the task of open-set relation prediction integrated with a pretrained open-set panoptic segmentation model to achieve true open-set panoptic scene graph generation (OpenPSG). Our OpenPSG leverages LMMs to achieve open-set relation prediction in an autoregressive manner. We introduce a relation query transformer to efficiently extract visual features of object pairs and estimate the existence of relations between them. The latter can enhance the prediction efficiency by filtering irrelevant pairs. Finally, we design the generation and judgement instructions to perform open-set relation prediction in PSG autoregressively. To our knowledge, we are the first to propose the open-set PSG task. Extensive experiments demonstrate that our method achieves state-of-the-art performance in open-set relation prediction and panoptic scene graph generation. Code is available at \url{https://github.com/franciszzj/OpenPSG}.
View PDF Chat

Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving

2024-06-24
Karim Armanious , Maurice Quach , Michaël Ulrich +7 more
This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD … This paper introduces the Bosch street dataset (BSD), a novel multi-modal large-scale dataset aimed at promoting highly automated driving (HAD) and advanced driver-assistance systems (ADAS) research. Unlike existing datasets, BSD offers a unique integration of high-resolution imaging radar, lidar, and camera sensors, providing unprecedented 360-degree coverage to bridge the current gap in high-resolution radar data availability. Spanning urban, rural, and highway environments, BSD enables detailed exploration into radar-based object detection and sensor fusion techniques. The dataset is aimed at facilitating academic and research collaborations between Bosch and current and future partners. This aims to foster joint efforts in developing cutting-edge HAD and ADAS technologies. The paper describes the dataset's key attributes, including its scalability, radar resolution, and labeling methodology. Key offerings also include initial benchmarks for sensor modalities and a development kit tailored for extensive data analysis and performance evaluation, underscoring our commitment to contributing valuable resources to the HAD and ADAS research community.
View PDF Chat

Redefining Automotive Radar Imaging: A Domain-Informed 1D Deep Learning Approach for High-Resolution and Efficient Performance

2024-06-11
Ruxin Zheng , Shunqiao Sun , Holger Caesar +2 more
Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for … Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for precise semantic scene interpretation. Classical super-resolution techniques adapted from optical imaging inadequately address the distinct characteristics of radar signal data. In response, our study redefines radar imaging super-resolution as a one-dimensional (1D) signal super-resolution spectra estimation problem by harnessing the radar signal processing domain knowledge, introducing innovative data normalization and a domain-informed signal-to-noise ratio (SNR)-guided loss function. Our tailored deep learning network for automotive radar imaging exhibits remarkable scalability, parameter efficiency and fast inference speed, alongside enhanced performance in terms of radar imaging quality and resolution. Extensive testing confirms that our SR-SPECNet sets a new benchmark in producing high-resolution radar range-azimuth images, outperforming existing methods across varied antenna configurations and dataset sizes. Source code and new radar dataset will be made publicly available online.
View PDF Chat

Label-Efficient 3D Object Detection For Road-Side Units

2024-06-02
Minh-Quan Dao , Holger Caesar , Julie Stephany Berrío +4 more
Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of … Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU), thus minimizing the impact of occlusion. While significant advancement has been made, the data-hungry nature of these methods creates a major hurdle for their real-world deployment, particularly due to the need for annotated RSU data. Manually annotating the vast amount of RSU data required for training is prohibitively expensive, given the sheer number of intersections and the effort involved in annotating point clouds. We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery. Our paper introduces two new modules: one for object discovery based on a spatial-temporal aggregation of point clouds, and another for refinement. Furthermore, we demonstrate that fine-tuning on a small portion of annotated data allows our object discovery models to narrow the performance gap with, or even surpass, fully supervised models. Extensive experiments are carried out in simulated and real-world datasets to evaluate our method.
View PDF Chat

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

2024-06-02
Shiming Wang , Holger Caesar , Liangliang Nan +1 more
View PDF Chat

Offline Tracking with Object Permanence

2024-06-02
Xianzhong Liu , Holger Caesar
View PDF Chat

UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes

2024-05-24
Ted Lentsch , Holger Caesar , Dariu M. Gavrila
Unsupervised 3D object detection methods have emerged to leverage vast amounts of data efficiently without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect … Unsupervised 3D object detection methods have emerged to leverage vast amounts of data efficiently without requiring manual labels for training. Recent approaches rely on dynamic objects for learning to detect objects but penalize the detections of static instances during training. Multiple rounds of (self) training are used in which detected static instances are added to the set of training targets; this procedure to improve performance is computationally expensive. To address this, we propose the method UNION. We use spatial clustering and self-supervised scene flow to obtain a set of static and dynamic object proposals from LiDAR. Subsequently, object proposals' visual appearances are encoded to distinguish static objects in the foreground and background by selecting static instances that are visually similar to dynamic objects. As a result, static and dynamic foreground objects are obtained together, and existing detectors can be trained with a single training. In addition, we extend 3D object discovery to detection by using object appearance-based cluster labels as pseudo-class labels for training object classification. We conduct extensive experiments on the nuScenes dataset and increase the state-of-the-art performance for unsupervised object discovery, i.e. UNION more than doubles the average precision to 33.9. The code will be made publicly available.
View PDF Chat

BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

2024-05-13
Jiarong Wei , Yancong Lin , Holger Caesar
View PDF Chat

Towards learning-based planning: The nuPlan benchmark for real-world autonomous driving

2024-05-13
Napat Karnchanachari , Dimitris Geromichalos , Kok Seang Tan +7 more
View PDF Chat

DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection

2024-04-03
Felix Fent , Andras Palffy , Holger Caesar
The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based … The perception of autonomous vehicles has to be efficient, robust, and cost-effective. However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based perception is still inferior to the others. Camera-radar fusion methods have been proposed to address this issue, but these are constrained by the typical sparsity of radar point clouds and often designed for radars without elevation information. We propose a novel camera-radar fusion approach called Dual Perspective Fusion Transformer (DPFT), designed to overcome these limitations. Our method leverages lower-level radar data (the radar cube) instead of the processed point clouds to preserve as much information as possible and employs projections in both the camera and ground planes to effectively use radars with elevation information and simplify the fusion with camera data. As a result, DPFT has demonstrated state-of-the-art performance on the K-Radar dataset while showing remarkable robustness against adverse weather conditions and maintaining a low inference time. The code is made available as open-source software under https://github.com/TUMFTM/DPFT.
View PDF Chat

Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving

2024-03-06
Napat Karnchanachari , Dimitris Geromichalos , Kok Seang Tan +7 more
Machine Learning (ML) has replaced traditional handcrafted methods for perception and prediction in autonomous vehicles. Yet for the equally important planning task, the adoption of ML-based techniques is slow. We … Machine Learning (ML) has replaced traditional handcrafted methods for perception and prediction in autonomous vehicles. Yet for the equally important planning task, the adoption of ML-based techniques is slow. We present nuPlan, the world's first real-world autonomous driving dataset, and benchmark. The benchmark is designed to test the ability of ML-based planners to handle diverse driving situations and to make safe and efficient decisions. To that end, we introduce a new large-scale dataset that consists of 1282 hours of diverse driving scenarios from 4 cities (Las Vegas, Boston, Pittsburgh, and Singapore) and includes high-quality auto-labeled object tracks and traffic light data. We exhaustively mine and taxonomize common and rare driving scenarios which are used during evaluation to get fine-grained insights into the performance and characteristics of a planner. Beyond the dataset, we provide a simulation and evaluation framework that enables a planner's actions to be simulated in closed-loop to account for interactions with other traffic participants. We present a detailed analysis of numerous baselines and investigate gaps between ML-based and traditional methods. Find the nuPlan dataset and code at nuplan.org.
View PDF Chat

ICP-Flow: LiDAR Scene Flow Estimation with ICP

2024-02-27
Yancong Lin , Holger Caesar
Scene flow characterizes the 3D motion between two LiDAR scans captured by an autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point-wise unconstrained flow vectors that can … Scene flow characterizes the 3D motion between two LiDAR scans captured by an autonomous vehicle at nearby timesteps. Prevalent methods consider scene flow as point-wise unconstrained flow vectors that can be learned by either large-scale training beforehand or time-consuming optimization at inference. However, these methods do not take into account that objects in autonomous driving often move rigidly. We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations. We propose ICP-Flow, a learning-free flow estimator. The core of our design is the conventional Iterative Closest Point (ICP) algorithm, which aligns the objects over time and outputs the corresponding rigid transformations. Crucially, to aid ICP, we propose a histogram-based initialization that discovers the most likely translation, thus providing a good starting point for ICP. The complete scene flow is then recovered from the rigid transformations. We outperform state-of-the-art baselines, including supervised models, on the Waymo dataset and perform competitively on Argoverse-v2 and nuScenes. Further, we train a feedforward neural network, supervised by the pseudo labels from our model, and achieve top performance among all models capable of real-time inference. We validate the advantage of our model on scene flow estimation with longer temporal gaps, up to 0.5 seconds where other models fail to deliver meaningful results.
View PDF Chat

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

2023-10-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to … Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods. Code is available at https://github.com/franciszzj/HiLo.
View PDF Chat

SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation

2023-06-01
Ted Lentsch , Zimin Xia , Holger Caesar +1 more
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which … This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view attention module for ground-view guided aerial feature selection and utilizes the geometric projection of the ground camera's viewing frustum on the aerial image to pool features. The efficient construction of aerial descriptors is achieved using precomputed masks. SliceMatch is trained using contrastive learning and pose estimation is formulated as a similarity comparison between the ground descriptor and the aerial descriptors. Compared to the state-of-the-art, SliceMatch achieves a 19% lower median localization error on the VIGOR benchmark using the same VGG16 backbone at 150 frames per second, and a 50% lower error when using a ResNet50 backbone.
View PDF Chat

HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation

2023-01-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to … Panoptic Scene Graph generation (PSG) is a recently proposed task in image scene understanding that aims to segment the image and extract triplets of subjects, objects and their relations to build a scene graph. This task is particularly challenging for two reasons. First, it suffers from a long-tail problem in its relation categories, making naive biased methods more inclined to high-frequency relations. Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations. Second, a subject-object pair can have two or more semantically overlapping relations. While existing methods favor one over the other, our proposed HiLo framework lets different network branches specialize on low and high frequency relations, enforce their consistency and fuse the results. To the best of our knowledge we are the first to propose an explicitly unbiased PSG method. In extensive experiments we show that our HiLo framework achieves state-of-the-art results on the PSG task. We also apply our method to the Scene Graph Generation task that predicts boxes instead of masks and see improvements over all baseline methods. Code is available at https://github.com/franciszzj/HiLo.
View PDF Chat

UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities

2023-01-01
Shiming Wang , Holger Caesar , Liangliang Nan +1 more
Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor … Multi-sensor object detection is an active research topic in automated driving, but the robustness of such detection models against missing sensor input (modality missing), e.g., due to a sudden sensor failure, is a critical problem which remains under-studied. In this work, we propose UniBEV, an end-to-end multi-modal 3D object detection framework designed for robustness against missing modalities: UniBEV can operate on LiDAR plus camera input, but also on LiDAR-only or camera-only input without retraining. To facilitate its detector head to handle different input combinations, UniBEV aims to create well-aligned Bird's Eye View (BEV) feature maps from each available modality. Unlike prior BEV-based multi-modal detection methods, all sensor modalities follow a uniform approach to resample features from the native sensor coordinate systems to the BEV features. We furthermore investigate the robustness of various fusion strategies w.r.t. missing modalities: the commonly used feature concatenation, but also channel-wise averaging, and a generalization to weighted averaging termed Channel Normalized Weights. To validate its effectiveness, we compare UniBEV to state-of-the-art BEVFusion and MetaBEV on nuScenes over all sensor input combinations. In this setting, UniBEV achieves $52.5 \%$ mAP on average over all input combinations, significantly improving over the baselines ($43.5 \%$ mAP on average for BEVFusion, $48.7 \%$ mAP on average for MetaBEV). An ablation study shows the robustness benefits of fusing by weighted averaging over regular concatenation, and of sharing queries between the BEV encoders of each modality. Our code will be released upon paper acceptance.

Offline Tracking with Object Permanence

2023-01-01
Xianzhong Liu , Holger Caesar
To reduce the expensive labor cost for manual labeling autonomous driving datasets, an alternative is to automatically label the datasets using an offline perception system. However, objects might be temporally … To reduce the expensive labor cost for manual labeling autonomous driving datasets, an alternative is to automatically label the datasets using an offline perception system. However, objects might be temporally occluded. Such occlusion scenarios in the datasets are common yet underexplored in offline auto labeling. In this work, we propose an offline tracking model that focuses on occluded object tracks. It leverages the concept of object permanence which means objects continue to exist even if they are not observed anymore. The model contains three parts: a standard online tracker, a re-identification (Re-ID) module that associates tracklets before and after occlusion, and a track completion module that completes the fragmented tracks. The Re-ID module and the track completion module use the vectorized map as one of the inputs to refine the tracking results with occlusion. The model can effectively recover the occluded object trajectories. It achieves state-of-the-art performance in 3D multi-object tracking by significantly improving the original online tracking result, showing its potential to be applied in offline auto labeling as a useful plugin to improve tracking by recovering occlusions.
View PDF Chat

BaSAL: Size Balanced Warm Start Active Learning for LiDAR Semantic Segmentation

2023-01-01
Jiarong Wei , Yancong Lin , Holger Caesar
Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then … Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data, and then training a model from these samples. We identify two problems with existing active learning methods for LiDAR semantic segmentation. First, they overlook the severe class imbalance inherent in LiDAR semantic segmentation datasets. Second, to bootstrap the active learning loop when there is no labeled data available, they train their initial model from randomly selected data samples, leading to low performance. This situation is referred to as the cold start problem. To address these problems we propose BaSAL, a size-balanced warm start active learning model, based on the observation that each object class has a characteristic size. By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced. Furthermore, in contrast to existing information measures like entropy or CoreSet, size-based sampling does not require a pretrained model, thus addressing the cold start problem effectively. Results show that we are able to improve the performance of the initial model by a large margin. Combining warm start and size-balanced sampling with established information measures, our approach achieves comparable performance to training on the entire SemanticKITTI dataset, despite using only 5% of the annotations, outperforming existing active learning methods. We also match the existing state-of-the-art in active learning on nuScenes. Our code is available at: https://github.com/Tony-WJR/BaSAL.

Graph Convolutional Networks for Complex Traffic Scenario Classification

2023-01-01
Tobias Hoek , Holger Caesar , Andreas Falkovén +1 more
A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems (ADS). Identifying these scenarios in an automated manner is … A scenario-based testing approach can reduce the time required to obtain statistically significant evidence of the safety of Automated Driving Systems (ADS). Identifying these scenarios in an automated manner is a challenging task. Most methods on scenario classification do not work for complex scenarios with diverse environments (highways, urban) and interaction with other traffic agents. This is mirrored in their approaches which model an individual vehicle in relation to its environment, but neglect the interaction between multiple vehicles (e.g. cut-ins, stationary lead vehicle). Furthermore, existing datasets lack diversity and do not have per-frame annotations to accurately learn the start and end time of a scenario. We propose a method for complex traffic scenario classification that is able to model the interaction of a vehicle with the environment, as well as other agents. We use Graph Convolutional Networks to model spatial and temporal aspects of these scenarios. Expanding the nuScenes and Argoverse 2 driving datasets, we introduce a scenario-labeled dataset, which covers different driving environments and is annotated per frame. Training our method on this dataset, we present a promising baseline for future research on per-frame complex scenario classification.

VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation

2023-01-01
Zijian Zhou , Miaojing Shi , Holger Caesar
Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations leads to unsatisfactory … Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects. However, the long-tail problem among relations leads to unsatisfactory results in real-world applications. Prior methods predominantly rely on vision information or utilize limited language information, such as object or relation names, thereby overlooking the utility of language information. Leveraging the recent progress in Large Language Models (LLMs), we propose to use language information to assist relation prediction, particularly for rare relations. To this end, we propose the Vision-Language Prompting (VLPrompt) model, which acquires vision information from images and language information from LLMs. Then, through a prompter network based on attention mechanism, it achieves precise relation prediction. Our extensive experiments show that VLPrompt significantly outperforms previous state-of-the-art methods on the PSG dataset, proving the effectiveness of incorporating language information and alleviating the long-tail problem of relations.
View PDF Chat

Panoptic Nuscenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

2022-02-07
Whye Kit Fong , Rohit Mohan , Juana Valeria Hurtado +4 more
Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, … Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, performing these tasks using LiDAR point clouds provides reliable predictions. However, existing datasets lack diversity in the type of urban scenes and have a limited number of dynamic object instances which hinders both learning of these tasks as well as credible benchmarking of the developed methods. In this letter, we introduce the large-scale Panoptic nuScenes benchmark dataset that extends our popular nuScenes dataset with point-wise groundtruth annotations for semantic segmentation, panoptic segmentation, and panoptic tracking tasks. To facilitate comparison, we provide several strong baselines for each of these tasks on our proposed dataset. Moreover, we analyze the drawbacks of the existing metrics for panoptic tracking and propose the novel instance-centric PAT metric that addresses the concerns. We present exhaustive experiments that demonstrate the utility of Panoptic nuScenes compared to existing datasets and make the online evaluation server available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nuScenes.org</uri> . We believe that this extension will accelerate the research of novel methods for scene understanding of dynamic urban environments.
View PDF Chat

SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation

2022-01-01
Ted Lentsch , Zimin Xia , Holger Caesar +1 more
This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which … This work addresses cross-view camera pose estimation, i.e., determining the 3-Degrees-of-Freedom camera pose of a given ground-level image w.r.t. an aerial image of the local area. We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor. The feature extractors extract dense features from the ground and aerial images. Given a set of candidate camera poses, the feature aggregators construct a single ground descriptor and a set of pose-dependent aerial descriptors. Notably, our novel aerial feature aggregator has a cross-view attention module for ground-view guided aerial feature selection and utilizes the geometric projection of the ground camera's viewing frustum on the aerial image to pool features. The efficient construction of aerial descriptors is achieved using precomputed masks. SliceMatch is trained using contrastive learning and pose estimation is formulated as a similarity comparison between the ground descriptor and the aerial descriptors. Compared to the state-of-the-art, SliceMatch achieves a 19% lower median localization error on the VIGOR benchmark using the same VGG16 backbone at 150 frames per second, and a 50% lower error when using a ResNet50 backbone.
View PDF Chat

nuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles.

2021-06-22
Holger Caesar , Juraj Kabzan , Kok Seang Tan +6 more
In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets … In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-scale driving dataset, lightweight closed-loop simulator, and motion-planning-specific metrics. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics. We plan to release the dataset at NeurIPS 2021 and organize benchmark challenges starting in early 2022.

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

2021-01-01
Whye Kit Fong , Rohit Mohan , Juana Valeria Hurtado +4 more
Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, … Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments. As LiDARs provide accurate illumination-independent geometric depictions of the scene, performing these tasks using LiDAR point clouds provides reliable predictions. However, existing datasets lack diversity in the type of urban scenes and have a limited number of dynamic object instances which hinders both learning of these tasks as well as credible benchmarking of the developed methods. In this paper, we introduce the large-scale Panoptic nuScenes benchmark dataset that extends our popular nuScenes dataset with point-wise groundtruth annotations for semantic segmentation, panoptic segmentation, and panoptic tracking tasks. To facilitate comparison, we provide several strong baselines for each of these tasks on our proposed dataset. Moreover, we analyze the drawbacks of the existing metrics for panoptic tracking and propose the novel instance-centric PAT metric that addresses the concerns. We present exhaustive experiments that demonstrate the utility of Panoptic nuScenes compared to existing datasets and make the online evaluation server available at nuScenes.org. We believe that this extension will accelerate the research of novel methods for scene understanding of dynamic urban environments.

NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles

2021-01-01
Holger Caesar , Juraj Kabzan , Kok Seang Tan +6 more
In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets … In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving. While there is a growing body of ML-based motion planners, the lack of established datasets and metrics has limited the progress in this area. Existing benchmarks for autonomous vehicle motion prediction have focused on short-term motion forecasting, rather than long-term planning. This has led previous works to use open-loop evaluation with L2-based metrics, which are not suitable for fairly evaluating long-term planning. Our benchmark overcomes these limitations by introducing a large-scale driving dataset, lightweight closed-loop simulator, and motion-planning-specific metrics. We provide a high-quality dataset with 1500h of human driving data from 4 cities across the US and Asia with widely varying traffic patterns (Boston, Pittsburgh, Las Vegas and Singapore). We will provide a closed-loop simulation framework with reactive agents and provide a large set of both general and scenario-specific planning metrics. We plan to release the dataset at NeurIPS 2021 and organize benchmark challenges starting in early 2022.
View PDF Chat

nuScenes: A Multimodal Dataset for Autonomous Driving

2020-06-01
Holger Caesar , Varun Bankiti , Alex Lang +7 more
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, … Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
View PDF Chat

The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes

2020-01-01
Yiluan Guo , Holger Caesar , Oscar Beijbom +2 more
A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and … A high-performing object detection system plays a crucial role in autonomous driving (AD). The performance, typically evaluated in terms of mean Average Precision, does not take into account orientation and distance of the actors in the scene, which are important for the safe AD. It also ignores environmental context. Recently, Philion et al. proposed a neural planning metric (PKL), based on the KL divergence of a planner's trajectory and the groundtruth route, to accommodate these requirements. In this paper, we use this neural planning metric to score all submissions of the nuScenes detection challenge and analyze the results. We find that while somewhat correlated with mAP, the PKL metric shows different behavior to increased traffic density, ego velocity, road curvature and intersections. Finally, we propose ideas to extend the neural planning metric.

PointPillars: Fast Encoders for Object Detection From Point Clouds

2019-06-01
Alex Lang , Sourabh Vora , Holger Caesar +3 more
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into … Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work, we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
View PDF Chat

nuScenes: A multimodal dataset for autonomous driving

2019-01-01
Holger Caesar , Varun Bankiti , Alex Lang +7 more
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, … Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2018-06-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff1, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.
View PDF Chat

PointPillars: Fast Encoders for Object Detection from Point Clouds

2018-01-01
Alex Lang , Sourabh Vora , Holger Caesar +3 more
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into … Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
View PDF Chat

Weakly Supervised Object Localization Using Things and Stuff Transfer

2017-10-01
Miaojing Shi , Holger Caesar , Vittorio Ferrari
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The … We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this, we acquire three types of knowledge from the source set: a segmentation model trained on both thing and stuff classes; similarity relations between target and source classes; and cooccurrence relations between thing and stuff classes in the source. The segmentation model is used to generate thing and stuff segmentation maps on a target image, while the class similarity and co-occurrence knowledge help refining them. We then incorporate these maps as new cues into a multiple instance learning framework (MIL), propagating the transferred knowledge from the pixel level to the object proposal level. In extensive experiments, we conduct our transfer from the PASCAL Context dataset (source) to the ILSVRC, COCO and PASCAL VOC 2007 datasets (targets). We evaluate our transfer across widely different thing classes, including some that are not similar in appearance, but appear against similar background. The results demonstrate significant improvement over standard MIL, and we outperform the state-of-the-art in the transfer setting.
View PDF Chat

Weakly Supervised Object Localization Using Things and Stuff Transfer

2017-01-01
Miaojing Shi , Holger Caesar , Vittorio Ferrari
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The … We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this, we acquire three types of knowledge from the source set: a segmentation model trained on both thing and stuff classes; similarity relations between target and source classes; and co-occurrence relations between thing and stuff classes in the source. The segmentation model is used to generate thing and stuff segmentation maps on a target image, while the class similarity and co-occurrence knowledge help refining them. We then incorporate these maps as new cues into a multiple instance learning framework (MIL), propagating the transferred knowledge from the pixel level to the object proposal level. In extensive experiments, we conduct our transfer from the PASCAL Context dataset (source) to the ILSVRC, COCO and PASCAL VOC 2007 datasets (targets). We evaluate our transfer across widely different thing classes, including some that are not similar in appearance, but appear against similar background. The results demonstrate significant improvement over standard MIL, and we outperform the state-of-the-art in the transfer setting.
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2016-12-12
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.

Region-based semantic segmentation with end-to-end training

2016-07-26
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main … We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0% on SIFT Flow and 49.9% on PASCAL Context, and is particularly accurate at object boundaries.

Region-Based Semantic Segmentation with End-to-End Training

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
View PDF Chat

COCO-Stuff: Thing and Stuff Classes in Context

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus … Semantic classes can be either things (objects with a well-defined shape, e.g. car, person) or stuff (amorphous background regions, e.g. grass, sky). While lots of classification and detection works focus on thing classes, less attention has been given to stuff classes. Nonetheless, stuff classes are important as they allow to explain important aspects of an image, including (1) scene type; (2) which thing classes are likely to be present and their location (through contextual reasoning); (3) physical attributes, material types and geometric properties of the scene. To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes. We introduce an efficient stuff annotation protocol based on superpixels, which leverages the original thing annotations. We quantify the speed versus quality trade-off of our protocol and explore the relation between annotation time and boundary complexity. Furthermore, we use COCO-Stuff to analyze: (a) the importance of stuff and thing classes in terms of their surface cover and how frequently they are mentioned in image captions; (b) the spatial relations between stuff and things, highlighting the rich contextual relations that make our dataset unique; (c) the performance of a modern semantic segmentation method on stuff and thing classes, and whether stuff is easier to segment than things.
View PDF Chat

Region-based semantic segmentation with end-to-end training

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main … We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0% on SIFT Flow and 49.9% on PASCAL Context, and is particularly accurate at object boundaries.
View PDF Chat

Joint Calibration for Semantic Segmentation

2015-07-06
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and … Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3) Each pixel can only be assigned to a single class, which creates competition between classes. We address all three problems with a joint calibration method which optimizes a multi-class loss defined over the final pixel-level output labeling, as opposed to simply region classification. Our method outperforms the state-of-the-art on the popular SIFT Flow [18] dataset in both the fully and weakly supervised setting by a considerably margin (+6% and +10%, respectively).

Joint Calibration for Semantic Segmentation

2015-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels … Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels in the training images. In the weakly supervised setting, class-labels are only given at the image-level. We tackle both settings in a single framework which builds on region-based classification. Our framework addresses three problems common to region-based semantic segmentation. First of all, objects naturally occur at different scales within an image [3]. Performing recognition at a single scale inevitably leads to regions covering only parts of an object which may have ambiguous appearance, and to regions straddling over multiple objects, whose classification is harder due to their mixed appearance. Therefore many recent methods operate on pools of regions computed at multiple scales, which have a much better chance of containing some regions covering complete objects [1, 2]. However, this leads to overlapping regions which may lead to conflicting class predictions at the pixel-level. These conflicts need to be properly resolved. Secondly, classes are often unbalanced [2, 4]: “cars” and “grass” are frequently found in images while “tricycles” and “gravel” are much rarer. Due to the nature of most classifiers, without careful consideration these rare classes are largely ignored: even if the class occurs in an image the system will rarely predict it. Since class-frequencies typically follow a power-law distribution, this problem becomes increasingly important with the modern trend towards larger datasets with more and more classes. Finally, classes compete: a pixel can only be assigned to a single class (e.g. it can not belong to both “sky” and “airplane”). To properly resolve such competition, a semantic segmentation framework should take into account predictions for multiple classes jointly. In this paper we address these three problems with a joint calibration method over a set of SVMs. Model. We represent an image by a set of overlapping regions [3] described by CNN features [1]. Our semantic segmentation model infers the label op of each pixel p in an image:
View PDF Chat

Joint Calibration for Semantic Segmentation

2015-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and … Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3) Each pixel can only be assigned to a single class, which creates competition between classes. We address all three problems with a joint calibration method which optimizes a multi-class loss defined over the final pixel-level output labeling, as opposed to simply region classification. Our method outperforms the state-of-the-art on the popular SIFT Flow [18] dataset in both the fully and weakly supervised setting by a considerably margin (+6% and +10%, respectively).
View PDF Chat
Coauthor Papers Together
Vittorio Ferrari 11
Oscar Beijbom 9
Jasper Uijlings 9
Alex Lang 6
Whye Kit Fong 6
Miaojing Shi 6
Sourabh Vora 4
Yancong Lin 4
Kok Seang Tan 4
Julian F. P. Kooij 4
Zijian Zhou 4
Ted Lentsch 3
Yiluan Guo 3
Shiming Wang 2
Xianzhong Liu 2
Napat Karnchanachari 2
Venice Erin Liong 2
Juana Valeria Hurtado 2
Liangliang Nan 2
Sammy Omari 2
Gianmarco Bernasconi 2
Abhinav Valada 2
Christopher Eriksen 2
Luke Fletcher 2
Juraj Kabzan 2
Rohit Mohan 2
Noushin Mehdipour 2
Lubing Zhou 2
Zimin Xia 2
Andras Palffy 2
Nanxiang Li 2
Varun Bankiti 2
Michael Teutsch 2
Alexander Wolpert 2
Dimitris Geromichalos 2
Jiarong Wei 2
Matthias Rapp 2
Shakiba Yaghoubi 2
Lubing Zhou 2
Ezio Malis 1
Philipp Rapp 1
Karim Armanious 1
Simon Gebraad 1
Krishnan Anush 1
Anush Krishnan 1
Giancarlo Baldan 1
Eric M. Wolff 1
Robin Gerster 1
Lukas Kohns 1
Timo Winterling 1

nuScenes: A Multimodal Dataset for Autonomous Driving

2020-06-01
Holger Caesar , Varun Bankiti , Alex Lang +7 more
Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, … Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image based benchmark datasets have driven development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar. As machine learning based methods for detection and tracking become more prevalent, there is a need to train and evaluate such methods on datasets containing range sensor data along with images. In this work we present nuTonomy scenes (nuScenes), the first dataset to carry the full autonomous vehicle sensor suite: 6 cameras, 5 radars and 1 lidar, all with full 360 degree field of view. nuScenes comprises 1000 scenes, each 20s long and fully annotated with 3D bounding boxes for 23 classes and 8 attributes. It has 7x as many annotations and 100x as many images as the pioneering KITTI dataset. We define novel 3D detection and tracking metrics. We also provide careful dataset analysis as well as baselines for lidar and image based detection and tracking. Data, development kit and more information are available online.
View PDF Chat

ImageNet Large Scale Visual Recognition Challenge

2015-04-10
Olga Russakovsky , Jia Deng , Hao Su +7 more
View PDF Chat

Fully convolutional networks for semantic segmentation

2015-06-01
Jonathan Long , Evan Shelhamer , Trevor Darrell
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight … Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.
View PDF Chat

Deep Residual Learning for Image Recognition

2016-06-01
Kaiming He , Xiangyu Zhang , Shaoqing Ren +1 more
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly … Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
View PDF Chat

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

2014-06-01
Ross Girshick , Jeff Donahue , Trevor Darrell +1 more
Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level … Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also present experiments that provide insight into what the network learns, revealing a rich hierarchy of image features. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.
View PDF Chat

Argoverse: 3D Tracking and Forecasting With Rich Maps

2019-06-01
Ming-Fang Chang , Deva Ramanan , James Hays +7 more
We present Argoverse, a dataset designed to support autonomous vehicle perception tasks including 3D tracking and motion forecasting. Argoverse includes sensor data collected by a fleet of autonomous vehicles in … We present Argoverse, a dataset designed to support autonomous vehicle perception tasks including 3D tracking and motion forecasting. Argoverse includes sensor data collected by a fleet of autonomous vehicles in Pittsburgh and Miami as well as 3D tracking annotations, 300k extracted interesting vehicle trajectories, and rich semantic maps. The sensor data consists of 360 degree images from 7 cameras with overlapping fields of view, forward-facing stereo imagery, 3D point clouds from long range LiDAR, and 6-DOF pose. Our 290km of mapped lanes contain rich geometric and semantic metadata which are not currently available in any public dataset. All data is released under a Creative Commons license at Argoverse.org. In baseline experiments, we use map information such as lane direction, driveable area, and ground height to improve the accuracy of 3D object tracking. We use 3D object tracking to mine for more than 300k interesting vehicle trajectories to create a trajectory forecasting benchmark. Motion forecasting experiments ranging in complexity from classical methods (k-NN) to LSTMs demonstrate that using detailed vector maps with lane-level information substantially reduces prediction error. Our tracking and forecasting experiments represent only a superficial exploration of the potential of rich maps in robotic perception. We hope that Argoverse will enable the research community to explore these problems in greater depth.
View PDF Chat

Recurrent Convolutional Neural Networks for Scene Parsing

2013-06-12
Pedro H. O. Pinheiro , Ronan Collobert
Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence … Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image long range dependencies. In a feed-forward architecture, this can be simply achieved by considering a sufficiently large input context patch, around each pixel to be labeled. We propose an approach consisting of a recurrent convolutional neural network which allows us to consider a large input context, while limiting the capacity of the model. Contrary to most standard approaches, our method does not rely on any segmentation methods, nor any task-specific features. The system is trained in an end-to-end manner over raw pixels, and models complex spatial dependencies with low inference cost. As the context size increases with the built-in recurrence, the system identifies and corrects its own errors. Our approach yields state-of-the-art performance on both the Stanford Background Dataset and the SIFT Flow Dataset, while remaining very fast at test time.

Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-scale Convolutional Architecture

2015-12-01
David Eigen , Rob Fergus
In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that … In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to each task using only small modifications, regressing from the input image to the output map directly. Our method progressively refines predictions using a sequence of scales, and captures many image details without any superpixels or low-level segmentation. We achieve state-of-the-art performance on benchmarks for all three tasks.
View PDF Chat

PointPillars: Fast Encoders for Object Detection From Point Clouds

2019-06-01
Alex Lang , Sourabh Vora , Holger Caesar +3 more
Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into … Object detection in point clouds is an important aspect of many robotics applications such as autonomous driving. In this paper, we consider the problem of encoding a point cloud into a format appropriate for a downstream detection pipeline. Recent literature suggests two types of encoders; fixed encoders tend to be fast but sacrifice accuracy, while encoders that are learned from data are more accurate, but slower. In this work, we propose PointPillars, a novel encoder which utilizes PointNets to learn a representation of point clouds organized in vertical columns (pillars). While the encoded features can be used with any standard 2D convolutional detection architecture, we further propose a lean downstream network. Extensive experimentation shows that PointPillars outperforms previous encoders with respect to both speed and accuracy by a large margin. Despite only using lidar, our full detection pipeline significantly outperforms the state of the art, even among fusion methods, with respect to both the 3D and bird's eye view KITTI benchmarks. This detection performance is achieved while running at 62 Hz: a 2 - 4 fold runtime improvement. A faster version of our method matches the state of the art at 105 Hz. These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
View PDF Chat

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

2014-01-01
Liang-Chieh Chen , George Papandreou , Iasonas Kokkinos +2 more
Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods … Deep Convolutional Neural Networks (DCNNs) have recently shown state of the art performance in high level vision tasks, such as image classification and object detection. This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification (also called "semantic image segmentation"). We show that responses at the final layer of DCNNs are not sufficiently localized for accurate object segmentation. This is due to the very invariance properties that make DCNNs good for high level tasks. We overcome this poor localization property of deep networks by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Qualitatively, our "DeepLab" system is able to localize segment boundaries at a level of accuracy which is beyond previous methods. Quantitatively, our method sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 71.6% IOU accuracy in the test set. We show how these results can be obtained efficiently: Careful network re-purposing and a novel application of the 'hole' algorithm from the wavelet community allow dense computation of neural net responses at 8 frames per second on a modern GPU.
View PDF Chat

Center-based 3D Object Detection and Tracking

2021-06-01
Tianwei Yin , Xingyi Zhou , Philipp Krähenbühl
Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world … Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional challenges. Objects in a 3D world do not follow any particular orientation, and box-based detectors have difficulties enumerating all orientations or fitting an axis-aligned bounding box to rotated objects. In this paper, we instead propose to represent, detect, and track 3D objects as points. Our framework, CenterPoint, first detects centers of objects using a keypoint detector and regresses to other attributes, including 3D size, 3D orientation, and velocity. In a second stage, it refines these estimates using additional point features on the object. In CenterPoint, 3D object tracking simplifies to greedy closest-point matching. The resulting detection and tracking algorithm is simple, efficient, and effective. CenterPoint achieved state-of-the-art performance on the nuScenes benchmark for both 3D detection and tracking, with 65.5 NDS and 63.8 AMOTA for a single model. On the Waymo Open Dataset, Center-Point outperforms all previous single model methods by a large margin and ranks first among all Lidar-only submissions. The code and pretrained models are available at https://github.com/tianweiy/CenterPoint.
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-01-01
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials

2012-01-01
Philipp Krähenbühl , Vladlen Koltun
Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are … Most state-of-the-art techniques for multi-class image segmentation and labeling use conditional random fields defined over pixels or image regions. While region-level models often feature dense pairwise connectivity, pixel-level models are considerably larger and have only permitted sparse graph structures. In this paper, we consider fully connected CRF models defined on the complete set of pixels in an image. The resulting graphs have billions of edges, making traditional inference algorithms impractical. Our main contribution is a highly efficient approximate inference algorithm for fully connected CRF models in which the pairwise edge potentials are defined by a linear combination of Gaussian kernels. Our experiments demonstrate that dense connectivity at the pixel level substantially improves segmentation and labeling accuracy.

Feedforward semantic segmentation with zoom-out features

2015-06-01
Mohammadreza Mostajabi , Payman Yadollahpour , Gregory Shakhnarovich
We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These … We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution. This approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead superpixels are classified by a feedforward multilayer network. Our architecture achieves 69.6% average accuracy on the PASCAL VOC 2012 test set.
View PDF Chat

Image parsing with a wide range of classes and scene-level context

2015-06-01
Marian George
This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood … This paper presents a nonparametric scene parsing approach that improves the overall accuracy, as well as the coverage of foreground classes in scene images. We first improve the label likelihood estimates at superpixels by merging likelihood scores from different probabilistic classifiers. This boosts the classification performance and enriches the representation of less-represented classes. Our second contribution consists of incorporating semantic context in the parsing process through global label costs. Our method does not rely on image retrieval sets but rather assigns a global likelihood estimate to each label, which is plugged into the overall energy function. We evaluate our system on two large-scale datasets, SIFTflow and LMSun. We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.
View PDF Chat

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

2019-01-01
Benjin Zhu , Zhengkai Jiang , Xiangxin Zhou +2 more
This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic … This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019). Generally, we utilize sparse 3D convolution to extract rich semantic features, which are then fed into a class-balanced multi-head network to perform 3D object detection. To handle the severe class imbalance problem inherent in the autonomous driving scenarios, we design a class-balanced sampling and augmentation strategy to generate a more balanced data distribution. Furthermore, we propose a balanced group-ing head to boost the performance for the categories withsimilar shapes. Based on the Challenge results, our methodoutperforms the PointPillars [14] baseline by a large mar-gin across all metrics, achieving state-of-the-art detection performance on the nuScenes dataset. Code will be released at CBGS.
View PDF Chat

The Cityscapes Dataset for Semantic Urban Scene Understanding

2016-06-01
Marius Cordts , Mohamed Omran , Sebastian Ramos +6 more
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of … Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations, 20 000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.
View PDF Chat

Deep hierarchical parsing for semantic segmentation

2015-06-01
Abhishek Sharma , Oncel Tuzel , David W. Jacobs
This paper proposes a learning-based approach to scene parsing inspired by the deep Recursive Context Propagation Network (RCPN). RCPN is a deep feed-forward neural network that utilizes the contextual information … This paper proposes a learning-based approach to scene parsing inspired by the deep Recursive Context Propagation Network (RCPN). RCPN is a deep feed-forward neural network that utilizes the contextual information from the entire image, through bottom-up followed by top-down context propagation via random binary parse trees. This improves the feature representation of every super-pixel in the image for better classification into semantic categories. We analyze RCPN and propose two novel contributions to further improve the model. We first analyze the learning of RCPN parameters and discover the presence of bypass error paths in the computation graph of RCPN that can hinder contextual propagation. We propose to tackle this problem by including the classification loss of the internal nodes of the random parse trees in the original RCPN loss function. Secondly, we use an MRF on the parse tree nodes to model the hierarchical dependency present in the output. Both modifications provide performance boosts over the original RCPN and the new system achieves state-of-the-art performance on Stanford Background, SIFT-Flow and Daimler urban datasets.
View PDF Chat

Focal Loss for Dense Object Detection

2017-10-01
Tsung-Yi Lin , Priya Goyal , Ross Girshick +2 more
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In … The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In this paper, we investigate why this is the case. We discover that the extreme foreground-background class imbalance encountered during training of dense detectors is the central cause. We propose to address this class imbalance by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples. Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. To evaluate the effectiveness of our loss, we design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors.
View PDF Chat

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

2016-06-06
Shaoqing Ren , Kaiming He , Ross Girshick +1 more
State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, … State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network(RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3], our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.
View PDF Chat

Convolutional feature masking for joint object and stuff segmentation

2015-06-01
Jifeng Dai , Kaiming He , Jian Sun
The topic of semantic segmentation has witnessed considerable progress due to the powerful features learned by convolutional neural networks (CNNs) [13]. The current leading approaches for semantic segmentation exploit shape … The topic of semantic segmentation has witnessed considerable progress due to the powerful features learned by convolutional neural networks (CNNs) [13]. The current leading approaches for semantic segmentation exploit shape information by extracting CNN features from masked image regions. This strategy introduces artificial boundaries on the images and may impact the quality of the extracted features. Besides, the operations on the raw image domain require to compute thousands of networks on a single image, which is time-consuming. In this paper, we propose to exploit shape information via masking convolutional features. The proposal segments (e.g., super-pixels) are treated as masks on the convolutional feature maps. The CNN features of segments are directly masked out from these maps and used to train classifiers for recognition. We further propose a joint method to handle objects and "stuff" (e.g., grass, sky, water) in the same framework. State-of-the-art results are demonstrated on benchmarks of PASCAL VOC and new PASCAL-CONTEXT, with a compelling computational speed.
View PDF Chat

Very Deep Convolutional Networks for Large-Scale Image Recognition

2014-09-04
Karen Simonyan , Andrew Zisserman
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks … In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

2018-06-01
Yin Zhou , Oncel Tuzel
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR … Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird's eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. Specifically, VoxelNet divides a point cloud into equally spaced 3D voxels and transforms a group of points within each voxel into a unified feature representation through the newly introduced voxel feature encoding (VFE) layer. In this way, the point cloud is encoded as a descriptive volumetric representation, which is then connected to a RPN to generate detections. Experiments on the KITTI car detection benchmark show that VoxelNet outperforms the state-of-the-art LiDAR based 3D detection methods by a large margin. Furthermore, our network learns an effective discriminative representation of objects with various geometries, leading to encouraging results in 3D detection of pedestrians and cyclists, based on only LiDAR.
View PDF Chat

Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset

2021-10-01
Scott Ettinger , Shuyang Cheng , Benjamin Caine +7 more
As autonomous driving systems mature, motion forecasting has received increasing attention as a critical requirement for planning. Of particular importance are interactive situations such as merges, unprotected turns, etc., where … As autonomous driving systems mature, motion forecasting has received increasing attention as a critical requirement for planning. Of particular importance are interactive situations such as merges, unprotected turns, etc., where predicting individual object motion is not sufficient. Joint predictions of multiple objects are required for effective route planning. There has been a critical need for high-quality motion data that is rich in both interactions and annotation to develop motion planning models. In this work, we introduce the most diverse interactive motion dataset to our knowledge, and provide specific labels for interacting objects suitable for developing joint prediction models. With over 100,000 scenes, each 20 seconds long at 10 Hz, our new dataset contains more than 570 hours of unique data over 1750 km of roadways. It was collected by mining for interesting interactions between vehicles, pedestrians, and cyclists across six cities within the United States. We use a high-accuracy 3D auto-labeling system to generate high quality 3D bounding boxes for each road agent, and provide corresponding high definition 3D maps for each scene. Furthermore, we introduce a new set of metrics that provides a comprehensive evaluation of both single agent and joint agent interaction motion forecasting models. Finally, we provide strong baseline models for individual-agent prediction and joint-prediction. We hope that this new large-scale interactive motion dataset will provide new opportunities for advancing motion forecasting models.
View PDF Chat

One Thousand and One Hours: Self-driving Motion Prediction Dataset

2020-01-01
John A. Houston , Guido Zuidhof , Luca Bergamini +6 more
Motivated by the impact of large-scale datasets on ML systems we present the largest self-driving dataset for motion prediction to date, containing over 1,000 hours of data. This was collected … Motivated by the impact of large-scale datasets on ML systems we present the largest self-driving dataset for motion prediction to date, containing over 1,000 hours of data. This was collected by a fleet of 20 autonomous vehicles along a fixed route in Palo Alto, California, over a four-month period. It consists of 170,000 scenes, where each scene is 25 seconds long and captures the perception output of the self-driving system, which encodes the precise positions and motions of nearby vehicles, cyclists, and pedestrians over time. On top of this, the dataset contains a high-definition semantic map with 15,242 labelled elements and a high-definition aerial view over the area. We show that using a dataset of this size dramatically improves performance for key self-driving problems. Combined with the provided software kit, this collection forms the largest and most detailed dataset to date for the development of self-driving machine learning tasks, such as motion forecasting, motion planning and simulation. The full dataset is available at http://level5.lyft.com/.

Attention Is All You Need

2017-01-01
Ashish Vaswani , Noam Shazeer , Niki Parmar +5 more
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an … The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

2016-02-26
Ramazan Gökberk Cinbiş , Jakob Verbeek , Cordelia Schmid
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. … Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCAL VOC 2007 dataset, which verifies the effectiveness of our approach.
View PDF Chat

Conditional Random Fields as Recurrent Neural Networks

2015-12-01
Shuai Zheng , Sadeep Jayasumana , Bernardino Romera‐Paredes +5 more
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to … Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate Conditional Random Fields with Gaussian pairwise potentials and mean-field approximate inference as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.
View PDF Chat

End-To-End Interpretable Neural Motion Planner

2019-06-01
Wenyuan Zeng , Wenjie Luo , Simon Su +4 more
In this paper, we propose a neural motion planner for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users. Towards this … In this paper, we propose a neural motion planner for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users. Towards this goal, we design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations in the form of 3D detections and their future trajectories, as well as a cost volume defining the goodness of each position that the self-driving car can take within the planning horizon. We then sample a set of diverse physically possible trajectories and choose the one with the minimum learned cost. Importantly, our cost volume is able to naturally capture multi-modality. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America. Our experiments show that the learned cost volume can generate safer planning than all the baselines.
View PDF Chat

Fully Connected Deep Structured Networks

2015-01-01
Alexander G. Schwing , Raquel Urtasun
Convolutional neural networks with many layers have recently been shown to achieve excellent results on many high-level tasks such as image classification, object detection and more recently also semantic segmentation. … Convolutional neural networks with many layers have recently been shown to achieve excellent results on many high-level tasks such as image classification, object detection and more recently also semantic segmentation. Particularly for semantic segmentation, a two-stage procedure is often employed. Hereby, convolutional networks are trained to provide good local pixel-wise features for the second step being traditionally a more global graphical model. In this work we unify this two-stage process into a single joint training algorithm. We demonstrate our method on the semantic image segmentation task and show encouraging results on the challenging PASCAL VOC 2012 dataset.

Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation

2016-06-01
Guosheng Lin , Chunhua Shen , Anton van den Hengel +1 more
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information, … Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information, specifically, we explore 'patch-patch' context between image regions, and 'patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to avoid repeated expensive CRF inference for back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image input and sliding pyramid pooling is effective for improving performance. Our experimental results set new state-of-the-art performance on a number of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC 2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an intersection-overunion score of 78:0 on the challenging PASCAL VOC 2012 dataset.
View PDF Chat

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

2015-12-01
Kaiming He , Xiangyu Zhang , Shaoqing Ren +1 more
Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified … Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit. PReLU improves model fitting with nearly zero extra computational cost and little overfitting risk. Second, we derive a robust initialization method that particularly considers the rectifier nonlinearities. This method enables us to train extremely deep rectified models directly from scratch and to investigate deeper or wider network architectures. Based on the learnable activation and advanced initialization, we achieve 4.94% top-5 test error on the ImageNet 2012 classification dataset. This is a 26% relative improvement over the ILSVRC 2014 winner (GoogLeNet, 6.66% [33]). To our knowledge, our result is the first to surpass the reported human-level performance (5.1%, [26]) on this dataset.
View PDF Chat

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

2014-02-23
Pierre Sermanet , David Eigen , Xiang Zhang +3 more
Abstract: We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a … Abstract: We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.

Frustum PointNets for 3D Object Detection from RGB-D Data

2018-06-01
Charles R. Qi , Wei Liu , Chenxia Wu +2 more
In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D … In this work, we study 3D object detection from RGBD data in both indoor and outdoor scenes. While previous methods focus on images or 3D voxels, often obscuring natural 3D patterns and invariances of 3D data, we directly operate on raw point clouds by popping up RGB-D scans. However, a key challenge of this approach is how to efficiently localize objects in point clouds of large-scale scenes (region proposal). Instead of solely relying on 3D proposals, our method leverages both mature 2D object detectors and advanced 3D deep learning for object localization, achieving efficiency as well as high recall for even small objects. Benefited from learning directly in raw point clouds, our method is also able to precisely estimate 3D bounding boxes even under strong occlusion or with very sparse points. Evaluated on KITTI and SUN RGB-D 3D detection benchmarks, our method outperforms the state of the art by remarkable margins while having real-time capability.
View PDF Chat

Joint Calibration for Semantic Segmentation

2015-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels … Semantic segmentation is the task of assigning a class label to each pixel in an image (Fig. 1). In the fully supervised setting, we have groundtruth labels for all pixels in the training images. In the weakly supervised setting, class-labels are only given at the image-level. We tackle both settings in a single framework which builds on region-based classification. Our framework addresses three problems common to region-based semantic segmentation. First of all, objects naturally occur at different scales within an image [3]. Performing recognition at a single scale inevitably leads to regions covering only parts of an object which may have ambiguous appearance, and to regions straddling over multiple objects, whose classification is harder due to their mixed appearance. Therefore many recent methods operate on pools of regions computed at multiple scales, which have a much better chance of containing some regions covering complete objects [1, 2]. However, this leads to overlapping regions which may lead to conflicting class predictions at the pixel-level. These conflicts need to be properly resolved. Secondly, classes are often unbalanced [2, 4]: “cars” and “grass” are frequently found in images while “tricycles” and “gravel” are much rarer. Due to the nature of most classifiers, without careful consideration these rare classes are largely ignored: even if the class occurs in an image the system will rarely predict it. Since class-frequencies typically follow a power-law distribution, this problem becomes increasingly important with the modern trend towards larger datasets with more and more classes. Finally, classes compete: a pixel can only be assigned to a single class (e.g. it can not belong to both “sky” and “airplane”). To properly resolve such competition, a semantic segmentation framework should take into account predictions for multiple classes jointly. In this paper we address these three problems with a joint calibration method over a set of SVMs. Model. We represent an image by a set of overlapping regions [3] described by CNN features [1]. Our semantic segmentation model infers the label op of each pixel p in an image:
View PDF Chat

Region-Based Semantic Segmentation with End-to-End Training

2016-01-01
Holger Caesar , Jasper Uijlings , Vittorio Ferrari
View PDF Chat

Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

2019-06-01
Yan Wang , Wei‐Lun Chao , Divyansh Garg +3 more
3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR … 3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper monocular or stereo imagery data have, until now, resulted in drastically lower accuracies --- a gap that is commonly attributed to poor image-based depth estimation. However, in this paper we argue that it is not the quality of the data but its representation that accounts for the majority of the difference. Taking the inner workings of convolutional neural networks into consideration, we propose to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal. With this representation we can apply different existing LiDAR-based detection algorithms. On the popular KITTI benchmark, our approach achieves impressive improvements over the existing state-of-the-art in image-based performance --- raising the detection accuracy of objects within the 30m range from the previous state-of-the-art of 22% to an unprecedented 74%. At the time of submission our algorithm holds the highest entry on the KITTI 3D object detection leaderboard for stereo-image-based approaches.
View PDF Chat

Click Carving: Segmenting Objects in Video with Point Clicks

2016-09-21
Suyog Dutt Jain , Kristen Grauman
We present a novel form of interactive video object segmentation where a few clicks by the user helps the system produce a full spatio-temporal segmentation of the object of interest. … We present a novel form of interactive video object segmentation where a few clicks by the user helps the system produce a full spatio-temporal segmentation of the object of interest. Whereas conventional interactive pipelines take the user's initialization as a starting point, we show the value in the system taking the lead even in initialization. In particular, for a given video frame, the system precomputes a ranked list of thousands of possible segmentation hypotheses (also referred to as object region proposals) using image and motion cues. Then, the user looks at the top ranked proposals, and clicks on the object boundary to carve away erroneous ones. This process iterates (typically 2-3 times), and each time the system revises the top ranked proposal set, until the user is satisfied with a resulting segmentation mask. Finally, the mask is propagated across the video to produce a spatio-temporal object tube. On three challenging datasets, we provide extensive comparisons with both existing work and simpler alternative methods. In all, the proposed Click Carving approach strikes an excellent balance of accuracy and human effort. It outperforms all similarly fast methods, and is competitive or better than those requiring 2 to 12 times the effort.
View PDF Chat

On learning to localize objects with minimal supervision

2014-01-01
Hyun Oh Song , Ross Girshick , Stefanie Jegelka +3 more
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a … Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a new method that achieves this goal with only image-level labels of whether the objects are present or not. Our approach combines a discriminative submodular cover problem for automatically discovering a set of positive object windows with a smoothed latent SVM formulation. The latter allows us to leverage efficient quasi-Newton optimization techniques. Our experiments demonstrate that the proposed approach provides a 50% relative improvement in mean average precision over the current state-of-the-art on PASCAL VOC 2007 detection.
View PDF Chat

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

2015-01-01
Jifeng Dai , Kaiming He , Jian Sun
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep … Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called BoxSup, produces competitive results supervised by boxes only, on par with strong baselines fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further unleashes the power of deep convolutional networks and yields state-of-the-art results on PASCAL VOC 2012 and PASCAL-CONTEXT.
View PDF Chat

Learning Deconvolution Network for Semantic Segmentation

2015-01-01
Hyeonwoo Noh , Seunghoon Hong , Bohyung Han
We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network … We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixel-wise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction; our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained with no external data through ensemble with the fully convolutional network.
View PDF Chat

Learning Deconvolution Network for Semantic Segmentation

2015-12-01
Hyeonwoo Noh , Seunghoon Hong , Bohyung Han
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution … We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixelwise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction, our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained without using Microsoft COCO dataset through ensemble with the fully convolutional network.
View PDF Chat

AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles

2017-11-02
Shital Shah , Debadeepta Dey , Chris Lovett +1 more
View PDF Chat

Training Deep Networks with Structured Layers by Matrix Backpropagation

2015-09-25
Catalin Ionescu , Orestis Vantzos , Cristian Sminchisescu
Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The … Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The power of deep networks stems both from their ability to perform local computations followed by pointwise non-linearities over increasingly larger receptive fields, and from the simplicity and scalability of the gradient-descent training procedure based on backpropagation. An open problem is the inclusion of layers that perform global, structured matrix computations like segmentation (e.g. normalized cuts) or higher-order pooling (e.g. log-tangent space metrics defined over the manifold of symmetric positive definite matrices) while preserving the validity and efficiency of an end-to-end deep training framework. In this paper we propose a sound mathematical apparatus to formally integrate global structured computation into deep computation architectures. At the heart of our methodology is the development of the theory and practice of backpropagation that generalizes to the calculus of adjoint matrix variations. The proposed matrix backpropagation methodology applies broadly to a variety of problems in machine learning or computational perception. Here we illustrate it by performing visual segmentation experiments using the BSDS and MSCOCO benchmarks, where we show that deep networks relying on second-order pooling and normalized cuts layers, trained end-to-end using matrix backpropagation, outperform counterparts that do not take advantage of such global layers.

Multi-view 3D Object Detection Network for Autonomous Driving

2017-07-01
Xiaozhi Chen , Huimin Ma , Ji Wan +2 more
This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images … This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the birds eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 14.9% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.
View PDF Chat

Material recognition in the wild with the Materials in Context Database

2015-06-01
Sean Bell , Paul Upchurch , Noah Snavely +1 more
Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make the problem particularly difficult. In this … Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make the problem particularly difficult. In this paper, we introduce a new, large-scale, open dataset of materials in the wild, the Materials in Context Database (MINC), and combine this dataset with deep learning to achieve material recognition and segmentation of images in the wild. MINC is an order of magnitude larger than previous material databases, while being more diverse and well-sampled across its 23 categories. Using MINC, we train convolutional neural networks (CNNs) for two tasks: classifying materials from patches, and simultaneous material recognition and segmentation in full images. For patch-based classification on MINC we found that the best performing CNN architectures can achieve 85.2% mean class accuracy. We convert these trained CNN classifiers into an efficient fully convolutional framework combined with a fully connected conditional random field (CRF) to predict the material at every pixel in an image, achieving 73.1% mean class accuracy. Our experiments demonstrate that having a large, well-sampled dataset such as MINC is crucial for real-world material recognition and segmentation.
View PDF Chat

Deep Continuous Fusion for Multi-Sensor 3D Object Detection

2020-01-01
Ming Liang , Bin Yang , Shenlong Wang +1 more
In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an … In this paper, we propose a novel 3D object detector that can exploit both LIDAR as well as cameras to perform very accurate localization. Towards this goal, we design an end-to-end learnable architecture that exploits continuous convolutions to fuse image and LIDAR feature maps at different levels of resolution. Our proposed continuous fusion layer encode both discrete-state image features as well as continuous geometric information. This enables us to design a novel, reliable and efficient end-to-end learnable 3D object detector based on multiple sensors. Our experimental evaluation on both KITTI as well as a large scale 3D object detection benchmark shows significant improvements over the state of the art.
View PDF Chat

Hypercolumns for object segmentation and fine-grained localization

2015-06-01
Bharath Hariharan , Pablo Arbeláez , Ross Girshick +1 more
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially … Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation [22], where we improve state-of-the-art from 49.7 mean AP <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">r</sup> [22] to 60.0, keypoint localization, where we get a 3.3 point boost over [20], and part labeling, where we show a 6.6 point gain over a strong baseline.
View PDF Chat

Describing Textures in the Wild

2014-06-01
Mircea Cimpoi , Subhransu Maji , Iasonas Kokkinos +2 more
Patterns and textures are key characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can … Patterns and textures are key characteristics of many natural objects: a shirt can be striped, the wings of a butterfly can be veined, and the skin of an animal can be scaly. Aiming at supporting this dimension in image understanding, we address the problem of describing textures with semantic attributes. We identify a vocabulary of forty-seven texture terms and use them to describe a large dataset of patterns collected "in the wild". The resulting Describable Textures Dataset (DTD) is a basis to seek the best representation for recognizing describable texture attributes in images. We port from object recognition to texture recognition the Improved Fisher Vector (IFV) and Deep Convolutional-network Activation Features (DeCAF), and show that surprisingly, they both outperform specialized texture descriptors not only on our problem, but also in established material recognition datasets. We also show that our describable attributes are excellent texture descriptors, transferring between datasets and tasks, in particular, combined with IFV and DeCAF, they significantly outperform the state-of-the-art by more than 10% on both FMD and KTH-TIPS-2b benchmarks. We also demonstrate that they produce intuitive descriptions of materials and Internet images.
View PDF Chat

From image-level to pixel-level labeling with Convolutional Networks

2015-06-01
Pedro O. Pinheiro , Ronan Collobert
We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as … We are interested in inferring object segmentation by leveraging only object class information, and by considering only minimal priors on the object segmentation task. This problem could be viewed as a kind of weakly supervised segmentation task, and naturally fits the Multiple Instance Learning (MIL) framework: every training image is known to have (or not) at least one pixel corresponding to the image class label, and the segmentation task can be rewritten as inferring the pixels belonging to the class of the object (given one image, and its object class). We propose a Convolutional Neural Network-based model, which is constrained during training to put more weight on pixels which are important for classifying the image. We show that at test time, the model has learned to discriminate the right pixels well enough, such that it performs very well on an existing segmentation benchmark, by adding only few smoothing priors. Our system is trained using a subset of the Imagenet dataset and the segmentation experiments are performed on the challenging Pascal VOC dataset (with no fine-tuning of the model on Pascal VOC). Our model beats the state of the art results in weakly supervised object segmentation task by a large margin. We also compare the performance of our model with state of the art fully-supervised segmentation approaches.
View PDF Chat