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

To boost or not to boost? On the limits of boosted trees for object detection

2016-12-01
Eshed Ohn-Bar , Mohan M. Trivedi
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), … We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
View PDF Chat

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-03-23
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.
View PDF Chat

Multi-scale volumes for deep object detection and localization

2016-06-17
Eshed Ohn-Bar , Mohan M. Trivedi
View PDF Chat

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges

2019-11-01
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near-collision is 0.75 seconds across the test videos. The project webpage can be found at https://aashi7.github.io/NearCollision.html.
View PDF Chat

Label Efficient Visual Abstractions for Autonomous Driving

2020-10-24
Aseem Behl , Kashyap Chitta , Aditya Prakash +2 more
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. … It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
View PDF Chat

Driver hand localization and grasp analysis: A vision-based real-time approach

2016-11-01
Siddharth , Akshay Rangesh , Eshed Ohn-Bar +1 more
Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes … Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes suffer from rapidly changing illumination and occlusion. This is aggravated by the fact that hands are highly deformable objects, and change in appearance frequently. This work addresses the task of accurately localizing driver hands and classifying the grasp state of each hand. We use a fast ConvNet to first detect likely hand regions. Next, a pixel-based skin classifier that takes into account the global illumination changes is used to refine the hand detections and remove false positives. This step generates a pixel-level mask for each hand. Finally, we study each such masked regions and detect if the driver is grasping the wheel, or in some cases a mobile phone. Through evaluation we demonstrate that our method can outperform state-of-the-art pixel based hand detectors, while running faster (at 35 fps) than other deep ConvNet based frameworks even for grasp analysis. Hand mask cues are shown to be crucial when analyzing a set of driver hand gestures (wheel/mobile phone grasp and no-grasp) in naturalistic driving settings. The proposed detection and localization pipeline hence can act as a general framework for real-time hand detection and gesture classification.
View PDF Chat

SelfD: Self-Learning Large-Scale Driving Policies From the Web

2022-06-01
Jimuyang Zhang , Ruizhao Zhu , Eshed Ohn-Bar
Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, … Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, scenarios, and geographical locations. However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse datafor complex 3D reasoning and planning tasks. Consequently, researchers have primarily focused on its use for various auxiliary pixel- and image-level computer vision tasks that do not consider an ultimate navigational objective. In this work, we introduce SelfD, a framework for learning scalable driving by utilizing large amounts of online monocular images. Our key idea is to leverage iterative semi-supervised training when learning imitative agents from unlabeled data. To handle unconstrained viewpoints, scenes, and camera parameters, we train an image-based model that directly learns to plan in the Bird's Eye View (BEV) space. Next, we use unla-beled data to augment the decision-making knowledge and robustness of an initially trained model via self-training. In particular, we propose a pseudo-labeling step which enables making full use of highly diverse demonstration data through "hypothetical" planning-based data augmentation. We employ a large dataset of publicly available YouTube videos to train SelfD and comprehensively analyze its generalization benefits across challenging navigation scenarios. Without requiring any additional data collection or annotation efforts, SelfD demonstrates consistent improvements (by up to 24%) in driving performance evaluation on nuScenes, Argoverse, Waymo, and CARLA.
View PDF Chat

Coaching a Teachable Student

2023-06-01
Jimuyang Zhang , Zanming Huang , Eshed Ohn-Bar
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods … We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods tend to result in suboptimal learned driving behavior by the student, which we hypothesize is due to inherent differences between the input, modeling capacity, and optimization processes of the two agents. We develop a novel distillation scheme that can address these limitations and close the gap between the sensorimotor agent and its privileged teacher. Our key insight is to design a student which learns to align their input features with the teacher's privileged Bird's Eye View (BEV) space. The student then can benefit from direct supervision by the teacher over the internal representation learning. To scaffold the difficult sensorimotor learning task, the student model is optimized via a student-paced coaching mechanism with various auxiliary supervision. We further propose a high-capacity imitation learned privileged agent that surpasses prior privileged agents in CARLA and ensures the student learns safe driving behavior. Our proposed sensorimotor agent results in a robust image-based behavior cloning agent in CARLA, improving over current models by over 20.6% in driving score without requiring LiDAR, historical observations, ensemble of models, on-policy data aggregation or reinforcement learning.
View PDF Chat

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges.

2019-03-21
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near collision is 0.75 seconds across the test videos.

Personalized Dynamics Models for Adaptive Assistive Navigation Systems

2018-01-01
Eshed Ohn-Bar , Kris Kitani , Chieko Asakawa
Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often … Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often operate in a generic, user-agnostic manner. However, to minimize confusion and navigation errors, our real-world analysis reveals a crucial need to adapt the instructional guidance across different end-users with diverse mobility skills. To address this practical issue in scalable system design, we propose a novel model-based reinforcement learning framework for personalizing the system-user interaction experience. When incrementally adapting the system to new users, we propose to use a weighted experts model for addressing data-efficiency limitations in transfer learning with deep models. A real-world dataset of navigation by blind users is used to show that the proposed approach allows for (1) more accurate long-term human behavior prediction (up to 20 seconds into the future) through improved reasoning over personal mobility characteristics, interaction with surrounding obstacles, and the current navigation goal, and (2) quick adaptation at the onset of learning, when data is limited.

XVO: Generalized Visual Odometry via Cross-Modal Self-Training

2023-10-01
Lei Lai , Zhongkai Shangguan , Jimuyang Zhang +1 more
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO … We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.
View PDF Chat

Personalized Dynamics Models for Adaptive Assistive Navigation Interfaces.

2018-04-11
Eshed Ohn-Bar , Kris Kitani , Chieko Asakawa
We explore the role of personalization for assistive navigational systems (e.g., service robot, wearable system or smartphone app) that guide visually impaired users through speech, sound and haptic-based instructional guidance. … We explore the role of personalization for assistive navigational systems (e.g., service robot, wearable system or smartphone app) that guide visually impaired users through speech, sound and haptic-based instructional guidance. Based on our analysis of real-world users, we show that the dynamics of blind users cannot be accounted for by a single universal model but instead must be learned on an individual basis. To learn personalized instructional interfaces, we propose PING (Personalized INstruction Generation agent), a model-based reinforcement learning framework which aims to quickly adapt its state transition dynamics model to match the reactions of the user using a novel end-to-end learned weighted majority-based regression algorithm. In our experiments, we show that PING learns dynamics models significantly faster compared to baseline transfer learning approaches on real-world data. We find that through better reasoning over personal mobility nuances, interaction with surrounding obstacles, and the current navigation task, PING is able to improve the performance of instructional assistive navigation at the most crucial junctions such as turns or veering paths. To enable sufficient planning time over user responses, we emphasize prediction of human motion for long horizons. Specifically, the learned dynamics models are shown to consistently improve long-term position prediction by over 1 meter on average (nearly the width of a hallway) compared to baseline approaches even when considering a prediction horizon of 20 seconds into the future.

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-03-12
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.

Learning to Drive Anywhere

2023-01-01
Ruizhao Zhu , Peng Huang , Eshed Ohn-Bar +1 more
Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e.g., left vs. right-hand traffic. In contrast, existing models for autonomous … Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e.g., left vs. right-hand traffic. In contrast, existing models for autonomous driving have been thus far only deployed within restricted operational domains, i.e., without accounting for varying driving behaviors across locations or model scalability. In this work, we propose AnyD, a single geographically-aware conditional imitation learning (CIL) model that can efficiently learn from heterogeneous and globally distributed data with dynamic environmental, traffic, and social characteristics. Our key insight is to introduce a high-capacity geo-location-based channel attention mechanism that effectively adapts to local nuances while also flexibly modeling similarities among regions in a data-driven manner. By optimizing a contrastive imitation objective, our proposed approach can efficiently scale across inherently imbalanced data distributions and location-dependent events. We demonstrate the benefits of our AnyD agent across multiple datasets, cities, and scalable deployment paradigms, i.e., centralized, semi-supervised, and distributed agent training. Specifically, AnyD outperforms CIL baselines by over 14% in open-loop evaluation and 30% in closed-loop testing on CARLA.
View PDF Chat

Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning

2018-06-22
Xinlei Pan , Eshed Ohn-Bar , Nicholas Rhinehart +3 more
Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task … Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal states. These subgoal states define a set of subtasks for the learning agent to complete in order to achieve the final goal. The learning agent queries for partial demonstrations corresponding to each subtask as needed when the agent struggles with the subtask. The proposed Human Interactive IRL (HI-IRL) framework is evaluated on several discrete path-planning tasks. We demonstrate that subgoal-based interactive structuring of the learning task results in significantly more efficient learning, requiring only a fraction of the demonstration data needed for learning the underlying reward function with the baseline IRL model.

Multi-scale Volumes for Deep Object Detection and Localization

2015-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection … This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection framework which operates on scale volumes of a deep feature pyramid is proposed. In contrast to the proposed approach, most current state-of-the-art object detectors operate on a single-scale in training, while testing involves independent evaluation across scales. One benefit of the proposed approach is in better capturing of multi-scale contextual information, resulting in significant gains in both detection performance and localization quality of objects on the PASCAL VOC dataset and a multi-view highway vehicles dataset. The joint detection and localization scale-specific models are shown to especially benefit detection of challenging object categories which exhibit large scale variation as well as detection of small objects.
View PDF Chat

Looking outside of the Box: Object Detection and Localization with Multi-scale Patterns.

2015-05-14
Eshed Ohn-Bar , Mohan M. Trivedi
Detection and localization of objects at multiple scales often involves sliding a single scale template in order to score windows at different scales independently. Nonetheless, multi-scale visual information at a … Detection and localization of objects at multiple scales often involves sliding a single scale template in order to score windows at different scales independently. Nonetheless, multi-scale visual information at a given image location is highly correlated. This fundamental insight allows us to generalize the traditional multi-scale sliding window technique by jointly considering image features at all scales in order to detect and localize objects. Two max-margin approaches are studied for learning the multi-scale templates and leveraging the highly structured multi-scale information which would have been ignored if a single-scale template was used. The multi-scale formulation is shown to significantly improve general detection performance (measured on the PASCAL VOC dataset). The experimental analysis shows the method to be effective with different visual features, both HOG and CNN. Surprisingly, for a given window in a specific scale, visual information from windows at the same image location but other scales (`out-of-scale' information) contains most of the discriminative information for detection.

Driver Hand Localization and Grasp Analysis: A Vision-based Real-time Approach

2018-01-01
Siddharth , Akshay Rangesh , Eshed Ohn-Bar +1 more
Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes … Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes suffer from rapidly changing illumination and occlusion. This is aggravated by the fact that hands are highly deformable objects, and change in appearance frequently. This work addresses the task of accurately localizing driver hands and classifying the grasp state of each hand. We use a fast ConvNet to first detect likely hand regions. Next, a pixel-based skin classifier that takes into account the global illumination changes is used to refine the hand detections and remove false positives. This step generates a pixel-level mask for each hand. Finally, we study each such masked regions and detect if the driver is grasping the wheel, or in some cases a mobile phone. Through evaluation we demonstrate that our method can outperform state-of-the-art pixel based hand detectors, while running faster (at 35 fps) than other deep ConvNet based frameworks even for grasp analysis. Hand mask cues are shown to be crucial when analyzing a set of driver hand gestures (wheel/mobile phone grasp and no-grasp) in naturalistic driving settings. The proposed detection and localization pipeline hence can act as a general framework for real-time hand detection and gesture classification.
View PDF Chat

Learning by Watching.

2021-06-10
Jimuyang Zhang , Eshed Ohn-Bar
When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing … When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.

SelfD: Self-Learning Large-Scale Driving Policies From the Web

2022-01-01
Jimuyang Zhang , Ruizhao Zhu , Eshed Ohn-Bar
Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, … Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, scenarios, and geographical locations. However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse data for complex 3D reasoning and planning tasks. Consequently, researchers have primarily focused on its use for various auxiliary pixel- and image-level computer vision tasks that do not consider an ultimate navigational objective. In this work, we introduce SelfD, a framework for learning scalable driving by utilizing large amounts of online monocular images. Our key idea is to leverage iterative semi-supervised training when learning imitative agents from unlabeled data. To handle unconstrained viewpoints, scenes, and camera parameters, we train an image-based model that directly learns to plan in the Bird's Eye View (BEV) space. Next, we use unlabeled data to augment the decision-making knowledge and robustness of an initially trained model via self-training. In particular, we propose a pseudo-labeling step which enables making full use of highly diverse demonstration data through "hypothetical" planning-based data augmentation. We employ a large dataset of publicly available YouTube videos to train SelfD and comprehensively analyze its generalization benefits across challenging navigation scenarios. Without requiring any additional data collection or annotation efforts, SelfD demonstrates consistent improvements (by up to 24%) in driving performance evaluation on nuScenes, Argoverse, Waymo, and CARLA.
View PDF Chat

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges

2019-01-01
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near collision is 0.75 seconds across the test videos.

Label Efficient Visual Abstractions for Autonomous Driving

2020-01-01
Aseem Behl , Kashyap Chitta , Aditya Prakash +2 more
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. … It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.

Learning by Watching

2021-01-01
Jimuyang Zhang , Eshed Ohn-Bar
When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing … When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.

To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection

2017-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), … We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
View PDF Chat

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.
View PDF Chat

Coaching a Teachable Student

2023-01-01
Jimuyang Zhang , Zanming Huang , Eshed Ohn-Bar
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods … We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods tend to result in suboptimal learned driving behavior by the student, which we hypothesize is due to inherent differences between the input, modeling capacity, and optimization processes of the two agents. We develop a novel distillation scheme that can address these limitations and close the gap between the sensorimotor agent and its privileged teacher. Our key insight is to design a student which learns to align their input features with the teacher's privileged Bird's Eye View (BEV) space. The student then can benefit from direct supervision by the teacher over the internal representation learning. To scaffold the difficult sensorimotor learning task, the student model is optimized via a student-paced coaching mechanism with various auxiliary supervision. We further propose a high-capacity imitation learned privileged agent that surpasses prior privileged agents in CARLA and ensures the student learns safe driving behavior. Our proposed sensorimotor agent results in a robust image-based behavior cloning agent in CARLA, improving over current models by over 20.6% in driving score without requiring LiDAR, historical observations, ensemble of models, on-policy data aggregation or reinforcement learning.
View PDF Chat

XVO: Generalized Visual Odometry via Cross-Modal Self-Training

2023-01-01
Lei Lai , Zhongkai Shangguan , Jimuyang Zhang +1 more
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO … We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.

UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning

2024-09-17
Kathakoli Sengupta , Zhongkai Shagguan , S. Bharadwaj +3 more
Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local … Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation tends to be restricted, offloading the computation, ie, to a remote server, can save local resources while providing access to high-quality predictions from powerful and large models. However, the resulting communication and latency overhead has led to limited usability of cloud models in dynamic, safety-critical, real-time settings. To effectively address this trade-off, we introduce UniLCD, a novel hybrid inference framework for enabling flexible local-cloud collaboration. By efficiently optimizing a flexible routing module via reinforcement learning and a suitable multi-task objective, UniLCD is specifically designed to support the multiple constraints of safety-critical end-to-end mobile systems. We validate the proposed approach using a challenging, crowded navigation task requiring frequent and timely switching between local and cloud operations. UniLCD demonstrates improved overall performance and efficiency, by over 35% compared to state-of-the-art baselines based on various split computing and early exit strategies.
View PDF Chat

Text to Blind Motion

2024-12-06
Hee Jae Kim , Kathakoli Sengupta , Masaki Kuribayashi +2 more
People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may … People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as veering more from a straight path or using touch-based exploration around curbs and obstacles. These behaviors may appear less predictable to motion models embedded in technologies such as autonomous vehicles. Yet, the ability of 3D motion models to capture such behavior has not been previously studied, as existing datasets for 3D human motion currently lack diversity and are biased toward people who are sighted. In this work, we introduce BlindWays, the first multimodal motion benchmark for pedestrians who are blind. We collect 3D motion data using wearable sensors with 11 blind participants navigating eight different routes in a real-world urban setting. Additionally, we provide rich textual descriptions that capture the distinctive movement characteristics of blind pedestrians and their interactions with both the navigation aid (e.g., a white cane or a guide dog) and the environment. We benchmark state-of-the-art 3D human prediction models, finding poor performance with off-the-shelf and pre-training-based methods for our novel task. To contribute toward safer and more reliable systems that can seamlessly reason over diverse human movements in their environments, our text-and-motion benchmark is available at https://blindways.github.io.
View PDF Chat

Scalable Early Childhood Reading Performance Prediction

2024-12-05
Zhongkai Shangguan , Zanming Huang , Eshed Ohn-Bar +4 more
Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational … Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational datasets for modeling and predicting future reading performance. In this work, we introduce the Enhanced Core Reading Instruction ECRI dataset, a novel large-scale longitudinal tabular dataset collected across 44 schools with 6,916 students and 172 teachers. We leverage the dataset to empirically evaluate the ability of state-of-the-art machine learning models to recognize early childhood educational patterns in multivariate and partial measurements. Specifically, we demonstrate a simple self-supervised strategy in which a Multi-Layer Perception (MLP) network is pre-trained over masked inputs to outperform several strong baselines while generalizing over diverse educational settings. To facilitate future developments in precise modeling and responsible use of models for individualized and early intervention strategies, our data and code are available at https://ecri-data.github.io/.
View PDF Chat

Text to Blind Motion

2024-12-06
Hee Jae Kim , Kathakoli Sengupta , Masaki Kuribayashi +2 more
People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may … People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as veering more from a straight path or using touch-based exploration around curbs and obstacles. These behaviors may appear less predictable to motion models embedded in technologies such as autonomous vehicles. Yet, the ability of 3D motion models to capture such behavior has not been previously studied, as existing datasets for 3D human motion currently lack diversity and are biased toward people who are sighted. In this work, we introduce BlindWays, the first multimodal motion benchmark for pedestrians who are blind. We collect 3D motion data using wearable sensors with 11 blind participants navigating eight different routes in a real-world urban setting. Additionally, we provide rich textual descriptions that capture the distinctive movement characteristics of blind pedestrians and their interactions with both the navigation aid (e.g., a white cane or a guide dog) and the environment. We benchmark state-of-the-art 3D human prediction models, finding poor performance with off-the-shelf and pre-training-based methods for our novel task. To contribute toward safer and more reliable systems that can seamlessly reason over diverse human movements in their environments, our text-and-motion benchmark is available at https://blindways.github.io.
View PDF Chat

Scalable Early Childhood Reading Performance Prediction

2024-12-05
Zhongkai Shangguan , Zanming Huang , Eshed Ohn-Bar +4 more
Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational … Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational datasets for modeling and predicting future reading performance. In this work, we introduce the Enhanced Core Reading Instruction ECRI dataset, a novel large-scale longitudinal tabular dataset collected across 44 schools with 6,916 students and 172 teachers. We leverage the dataset to empirically evaluate the ability of state-of-the-art machine learning models to recognize early childhood educational patterns in multivariate and partial measurements. Specifically, we demonstrate a simple self-supervised strategy in which a Multi-Layer Perception (MLP) network is pre-trained over masked inputs to outperform several strong baselines while generalizing over diverse educational settings. To facilitate future developments in precise modeling and responsible use of models for individualized and early intervention strategies, our data and code are available at https://ecri-data.github.io/.
View PDF Chat

UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning

2024-09-17
Kathakoli Sengupta , Zhongkai Shagguan , S. Bharadwaj +3 more
Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local … Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation tends to be restricted, offloading the computation, ie, to a remote server, can save local resources while providing access to high-quality predictions from powerful and large models. However, the resulting communication and latency overhead has led to limited usability of cloud models in dynamic, safety-critical, real-time settings. To effectively address this trade-off, we introduce UniLCD, a novel hybrid inference framework for enabling flexible local-cloud collaboration. By efficiently optimizing a flexible routing module via reinforcement learning and a suitable multi-task objective, UniLCD is specifically designed to support the multiple constraints of safety-critical end-to-end mobile systems. We validate the proposed approach using a challenging, crowded navigation task requiring frequent and timely switching between local and cloud operations. UniLCD demonstrates improved overall performance and efficiency, by over 35% compared to state-of-the-art baselines based on various split computing and early exit strategies.
View PDF Chat

XVO: Generalized Visual Odometry via Cross-Modal Self-Training

2023-10-01
Lei Lai , Zhongkai Shangguan , Jimuyang Zhang +1 more
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO … We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.
View PDF Chat

Coaching a Teachable Student

2023-06-01
Jimuyang Zhang , Zanming Huang , Eshed Ohn-Bar
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods … We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods tend to result in suboptimal learned driving behavior by the student, which we hypothesize is due to inherent differences between the input, modeling capacity, and optimization processes of the two agents. We develop a novel distillation scheme that can address these limitations and close the gap between the sensorimotor agent and its privileged teacher. Our key insight is to design a student which learns to align their input features with the teacher's privileged Bird's Eye View (BEV) space. The student then can benefit from direct supervision by the teacher over the internal representation learning. To scaffold the difficult sensorimotor learning task, the student model is optimized via a student-paced coaching mechanism with various auxiliary supervision. We further propose a high-capacity imitation learned privileged agent that surpasses prior privileged agents in CARLA and ensures the student learns safe driving behavior. Our proposed sensorimotor agent results in a robust image-based behavior cloning agent in CARLA, improving over current models by over 20.6% in driving score without requiring LiDAR, historical observations, ensemble of models, on-policy data aggregation or reinforcement learning.
View PDF Chat

Coaching a Teachable Student

2023-01-01
Jimuyang Zhang , Zanming Huang , Eshed Ohn-Bar
We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods … We propose a novel knowledge distillation framework for effectively teaching a sensorimotor student agent to drive from the supervision of a privileged teacher agent. Current distillation for sensorimotor agents methods tend to result in suboptimal learned driving behavior by the student, which we hypothesize is due to inherent differences between the input, modeling capacity, and optimization processes of the two agents. We develop a novel distillation scheme that can address these limitations and close the gap between the sensorimotor agent and its privileged teacher. Our key insight is to design a student which learns to align their input features with the teacher's privileged Bird's Eye View (BEV) space. The student then can benefit from direct supervision by the teacher over the internal representation learning. To scaffold the difficult sensorimotor learning task, the student model is optimized via a student-paced coaching mechanism with various auxiliary supervision. We further propose a high-capacity imitation learned privileged agent that surpasses prior privileged agents in CARLA and ensures the student learns safe driving behavior. Our proposed sensorimotor agent results in a robust image-based behavior cloning agent in CARLA, improving over current models by over 20.6% in driving score without requiring LiDAR, historical observations, ensemble of models, on-policy data aggregation or reinforcement learning.
View PDF Chat

Learning to Drive Anywhere

2023-01-01
Ruizhao Zhu , Peng Huang , Eshed Ohn-Bar +1 more
Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e.g., left vs. right-hand traffic. In contrast, existing models for autonomous … Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e.g., left vs. right-hand traffic. In contrast, existing models for autonomous driving have been thus far only deployed within restricted operational domains, i.e., without accounting for varying driving behaviors across locations or model scalability. In this work, we propose AnyD, a single geographically-aware conditional imitation learning (CIL) model that can efficiently learn from heterogeneous and globally distributed data with dynamic environmental, traffic, and social characteristics. Our key insight is to introduce a high-capacity geo-location-based channel attention mechanism that effectively adapts to local nuances while also flexibly modeling similarities among regions in a data-driven manner. By optimizing a contrastive imitation objective, our proposed approach can efficiently scale across inherently imbalanced data distributions and location-dependent events. We demonstrate the benefits of our AnyD agent across multiple datasets, cities, and scalable deployment paradigms, i.e., centralized, semi-supervised, and distributed agent training. Specifically, AnyD outperforms CIL baselines by over 14% in open-loop evaluation and 30% in closed-loop testing on CARLA.
View PDF Chat

XVO: Generalized Visual Odometry via Cross-Modal Self-Training

2023-01-01
Lei Lai , Zhongkai Shangguan , Jimuyang Zhang +1 more
We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO … We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.

SelfD: Self-Learning Large-Scale Driving Policies From the Web

2022-06-01
Jimuyang Zhang , Ruizhao Zhu , Eshed Ohn-Bar
Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, … Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, scenarios, and geographical locations. However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse datafor complex 3D reasoning and planning tasks. Consequently, researchers have primarily focused on its use for various auxiliary pixel- and image-level computer vision tasks that do not consider an ultimate navigational objective. In this work, we introduce SelfD, a framework for learning scalable driving by utilizing large amounts of online monocular images. Our key idea is to leverage iterative semi-supervised training when learning imitative agents from unlabeled data. To handle unconstrained viewpoints, scenes, and camera parameters, we train an image-based model that directly learns to plan in the Bird's Eye View (BEV) space. Next, we use unla-beled data to augment the decision-making knowledge and robustness of an initially trained model via self-training. In particular, we propose a pseudo-labeling step which enables making full use of highly diverse demonstration data through "hypothetical" planning-based data augmentation. We employ a large dataset of publicly available YouTube videos to train SelfD and comprehensively analyze its generalization benefits across challenging navigation scenarios. Without requiring any additional data collection or annotation efforts, SelfD demonstrates consistent improvements (by up to 24%) in driving performance evaluation on nuScenes, Argoverse, Waymo, and CARLA.
View PDF Chat

SelfD: Self-Learning Large-Scale Driving Policies From the Web

2022-01-01
Jimuyang Zhang , Ruizhao Zhu , Eshed Ohn-Bar
Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, … Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, scenarios, and geographical locations. However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse data for complex 3D reasoning and planning tasks. Consequently, researchers have primarily focused on its use for various auxiliary pixel- and image-level computer vision tasks that do not consider an ultimate navigational objective. In this work, we introduce SelfD, a framework for learning scalable driving by utilizing large amounts of online monocular images. Our key idea is to leverage iterative semi-supervised training when learning imitative agents from unlabeled data. To handle unconstrained viewpoints, scenes, and camera parameters, we train an image-based model that directly learns to plan in the Bird's Eye View (BEV) space. Next, we use unlabeled data to augment the decision-making knowledge and robustness of an initially trained model via self-training. In particular, we propose a pseudo-labeling step which enables making full use of highly diverse demonstration data through "hypothetical" planning-based data augmentation. We employ a large dataset of publicly available YouTube videos to train SelfD and comprehensively analyze its generalization benefits across challenging navigation scenarios. Without requiring any additional data collection or annotation efforts, SelfD demonstrates consistent improvements (by up to 24%) in driving performance evaluation on nuScenes, Argoverse, Waymo, and CARLA.
View PDF Chat

Learning by Watching.

2021-06-10
Jimuyang Zhang , Eshed Ohn-Bar
When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing … When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.

Learning by Watching

2021-01-01
Jimuyang Zhang , Eshed Ohn-Bar
When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing … When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.

Label Efficient Visual Abstractions for Autonomous Driving

2020-10-24
Aseem Behl , Kashyap Chitta , Aditya Prakash +2 more
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. … It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
View PDF Chat

Label Efficient Visual Abstractions for Autonomous Driving

2020-01-01
Aseem Behl , Kashyap Chitta , Aditya Prakash +2 more
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. … It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges

2019-11-01
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near-collision is 0.75 seconds across the test videos. The project webpage can be found at https://aashi7.github.io/NearCollision.html.
View PDF Chat

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges.

2019-03-21
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near collision is 0.75 seconds across the test videos.

Forecasting Time-to-Collision from Monocular Video: Feasibility, Dataset, and Challenges

2019-01-01
Aashi Manglik , Xinshuo Weng , Eshed Ohn-Bar +1 more
We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We … We explore the possibility of using a single monocular camera to forecast the time to collision between a suitcase-shaped robot being pushed by its user and other nearby pedestrians. We develop a purely image-based deep learning approach that directly estimates the time to collision without the need of relying on explicit geometric depth estimates or velocity information to predict future collisions. While previous work has focused on detecting immediate collision in the context of navigating Unmanned Aerial Vehicles, the detection was limited to a binary variable (i.e., collision or no collision). We propose a more fine-grained approach to collision forecasting by predicting the exact time to collision in terms of milliseconds, which is more helpful for collision avoidance in the context of dynamic path planning. To evaluate our method, we have collected a novel dataset of over 13,000 indoor video segments each showing a trajectory of at least one person ending in a close proximity (a near collision) with the camera mounted on a mobile suitcase-shaped platform. Using this dataset, we do extensive experimentation on different temporal windows as input using an exhaustive list of state-of-the-art convolutional neural networks (CNNs). Our results show that our proposed multi-stream CNN is the best model for predicting time to near-collision. The average prediction error of our time to near collision is 0.75 seconds across the test videos.

Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning

2018-06-22
Xinlei Pan , Eshed Ohn-Bar , Nicholas Rhinehart +3 more
Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task … Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal states. These subgoal states define a set of subtasks for the learning agent to complete in order to achieve the final goal. The learning agent queries for partial demonstrations corresponding to each subtask as needed when the agent struggles with the subtask. The proposed Human Interactive IRL (HI-IRL) framework is evaluated on several discrete path-planning tasks. We demonstrate that subgoal-based interactive structuring of the learning task results in significantly more efficient learning, requiring only a fraction of the demonstration data needed for learning the underlying reward function with the baseline IRL model.

Personalized Dynamics Models for Adaptive Assistive Navigation Interfaces.

2018-04-11
Eshed Ohn-Bar , Kris Kitani , Chieko Asakawa
We explore the role of personalization for assistive navigational systems (e.g., service robot, wearable system or smartphone app) that guide visually impaired users through speech, sound and haptic-based instructional guidance. … We explore the role of personalization for assistive navigational systems (e.g., service robot, wearable system or smartphone app) that guide visually impaired users through speech, sound and haptic-based instructional guidance. Based on our analysis of real-world users, we show that the dynamics of blind users cannot be accounted for by a single universal model but instead must be learned on an individual basis. To learn personalized instructional interfaces, we propose PING (Personalized INstruction Generation agent), a model-based reinforcement learning framework which aims to quickly adapt its state transition dynamics model to match the reactions of the user using a novel end-to-end learned weighted majority-based regression algorithm. In our experiments, we show that PING learns dynamics models significantly faster compared to baseline transfer learning approaches on real-world data. We find that through better reasoning over personal mobility nuances, interaction with surrounding obstacles, and the current navigation task, PING is able to improve the performance of instructional assistive navigation at the most crucial junctions such as turns or veering paths. To enable sufficient planning time over user responses, we emphasize prediction of human motion for long horizons. Specifically, the learned dynamics models are shown to consistently improve long-term position prediction by over 1 meter on average (nearly the width of a hallway) compared to baseline approaches even when considering a prediction horizon of 20 seconds into the future.

Driver Hand Localization and Grasp Analysis: A Vision-based Real-time Approach

2018-01-01
Siddharth , Akshay Rangesh , Eshed Ohn-Bar +1 more
Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes … Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes suffer from rapidly changing illumination and occlusion. This is aggravated by the fact that hands are highly deformable objects, and change in appearance frequently. This work addresses the task of accurately localizing driver hands and classifying the grasp state of each hand. We use a fast ConvNet to first detect likely hand regions. Next, a pixel-based skin classifier that takes into account the global illumination changes is used to refine the hand detections and remove false positives. This step generates a pixel-level mask for each hand. Finally, we study each such masked regions and detect if the driver is grasping the wheel, or in some cases a mobile phone. Through evaluation we demonstrate that our method can outperform state-of-the-art pixel based hand detectors, while running faster (at 35 fps) than other deep ConvNet based frameworks even for grasp analysis. Hand mask cues are shown to be crucial when analyzing a set of driver hand gestures (wheel/mobile phone grasp and no-grasp) in naturalistic driving settings. The proposed detection and localization pipeline hence can act as a general framework for real-time hand detection and gesture classification.
View PDF Chat

Personalized Dynamics Models for Adaptive Assistive Navigation Systems

2018-01-01
Eshed Ohn-Bar , Kris Kitani , Chieko Asakawa
Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often … Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often operate in a generic, user-agnostic manner. However, to minimize confusion and navigation errors, our real-world analysis reveals a crucial need to adapt the instructional guidance across different end-users with diverse mobility skills. To address this practical issue in scalable system design, we propose a novel model-based reinforcement learning framework for personalizing the system-user interaction experience. When incrementally adapting the system to new users, we propose to use a weighted experts model for addressing data-efficiency limitations in transfer learning with deep models. A real-world dataset of navigation by blind users is used to show that the proposed approach allows for (1) more accurate long-term human behavior prediction (up to 20 seconds into the future) through improved reasoning over personal mobility characteristics, interaction with surrounding obstacles, and the current navigation goal, and (2) quick adaptation at the onset of learning, when data is limited.

To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection

2017-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), … We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
View PDF Chat

To boost or not to boost? On the limits of boosted trees for object detection

2016-12-01
Eshed Ohn-Bar , Mohan M. Trivedi
We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), … We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.
View PDF Chat

Driver hand localization and grasp analysis: A vision-based real-time approach

2016-11-01
Siddharth , Akshay Rangesh , Eshed Ohn-Bar +1 more
Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes … Extracting hand regions and their grasp information from images robustly in real-time is critical for occupants' safety and in-vehicular infotainment applications. It must however, be noted that naturalistic driving scenes suffer from rapidly changing illumination and occlusion. This is aggravated by the fact that hands are highly deformable objects, and change in appearance frequently. This work addresses the task of accurately localizing driver hands and classifying the grasp state of each hand. We use a fast ConvNet to first detect likely hand regions. Next, a pixel-based skin classifier that takes into account the global illumination changes is used to refine the hand detections and remove false positives. This step generates a pixel-level mask for each hand. Finally, we study each such masked regions and detect if the driver is grasping the wheel, or in some cases a mobile phone. Through evaluation we demonstrate that our method can outperform state-of-the-art pixel based hand detectors, while running faster (at 35 fps) than other deep ConvNet based frameworks even for grasp analysis. Hand mask cues are shown to be crucial when analyzing a set of driver hand gestures (wheel/mobile phone grasp and no-grasp) in naturalistic driving settings. The proposed detection and localization pipeline hence can act as a general framework for real-time hand detection and gesture classification.
View PDF Chat

Multi-scale volumes for deep object detection and localization

2016-06-17
Eshed Ohn-Bar , Mohan M. Trivedi
View PDF Chat

Looking outside of the Box: Object Detection and Localization with Multi-scale Patterns.

2015-05-14
Eshed Ohn-Bar , Mohan M. Trivedi
Detection and localization of objects at multiple scales often involves sliding a single scale template in order to score windows at different scales independently. Nonetheless, multi-scale visual information at a … Detection and localization of objects at multiple scales often involves sliding a single scale template in order to score windows at different scales independently. Nonetheless, multi-scale visual information at a given image location is highly correlated. This fundamental insight allows us to generalize the traditional multi-scale sliding window technique by jointly considering image features at all scales in order to detect and localize objects. Two max-margin approaches are studied for learning the multi-scale templates and leveraging the highly structured multi-scale information which would have been ignored if a single-scale template was used. The multi-scale formulation is shown to significantly improve general detection performance (measured on the PASCAL VOC dataset). The experimental analysis shows the method to be effective with different visual features, both HOG and CNN. Surprisingly, for a given window in a specific scale, visual information from windows at the same image location but other scales (`out-of-scale' information) contains most of the discriminative information for detection.

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-03-23
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.
View PDF Chat

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-03-12
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.

Multi-scale Volumes for Deep Object Detection and Localization

2015-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection … This study aims to analyze the benefits of improved multi-scale reasoning for object detection and localization with deep convolutional neural networks. To that end, an efficient and general object detection framework which operates on scale volumes of a deep feature pyramid is proposed. In contrast to the proposed approach, most current state-of-the-art object detectors operate on a single-scale in training, while testing involves independent evaluation across scales. One benefit of the proposed approach is in better capturing of multi-scale contextual information, resulting in significant gains in both detection performance and localization quality of objects on the PASCAL VOC dataset and a multi-view highway vehicles dataset. The joint detection and localization scale-specific models are shown to especially benefit detection of challenging object categories which exhibit large scale variation as well as detection of small objects.
View PDF Chat

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-01-01
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means for dealing with intra-category diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.
View PDF Chat
Coauthor Papers Together
Mohan M. Trivedi 10
Jimuyang Zhang 8
Kris Kitani 5
Zhongkai Shangguan 3
Xinshuo Weng 3
Zanming Huang 3
Aashi Manglik 3
Chieko Asakawa 2
Lei Lai 2
Andreas Geiger 2
Aseem Behl 2
Kathakoli Sengupta 2
Ruizhao Zhu 2
Akshay Rangesh 2
Kashyap Chitta 2
Siddharth 2
S. Arora 1
Hee Jae Kim 1
Hank Fien 1
Michael Stoolmiller 1
Ruizhao Zhu 1
Zhongkai Shagguan 1
Derek Kosty 1
Ola Ozernov‐Palchik 1
Hernisa Kacorri 1
Yan Xu 1
Aditya Prakash 1
Renato Mancuso 1
Masaki Kuribayashi 1
Venkatesh Saligrama 1
Yilin Shen 1
Kris M. Kitanil 1
Xinlei Pan 1
Nicholas Rhinehart 1
Peng Huang 1
Aditya Prakash 1
S. Bharadwaj 1

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

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

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.

LaTeS: Latent Space Distillation for Teacher-Student Driving Policy Learning.

2019-12-06
Albert Zhao , Tong He , Yitao Liang +3 more

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving

2015-12-01
Chenyi Chen , Ari Seff , Alain L. Kornhauser +1 more
Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly … Today, there are two major paradigms for vision-based autonomous driving systems: mediated perception approaches that parse an entire scene to make a driving decision, and behavior reflex approaches that directly map an input image to a driving action by a regressor. In this paper, we propose a third paradigm: a direct perception approach to estimate the affordance for driving. We propose to map an input image to a small number of key perception indicators that directly relate to the affordance of a road/traffic state for driving. Our representation provides a set of compact yet complete descriptions of the scene to enable a simple controller to drive autonomously. Falling in between the two extremes of mediated perception and behavior reflex, we argue that our direct perception representation provides the right level of abstraction. To demonstrate this, we train a deep Convolutional Neural Network using recording from 12 hours of human driving in a video game and show that our model can work well to drive a car in a very diverse set of virtual environments. We also train a model for car distance estimation on the KITTI dataset. Results show that our direct perception approach can generalize well to real driving images. Source code and data are available on our project website.
View PDF Chat

End-to-End Driving Via Conditional Imitation Learning

2018-05-01
Felipe Codevilla , Matthias Müller , Antonio M. López +2 more
Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A … Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands.
View PDF Chat

Exploring the Limitations of Behavior Cloning for Autonomous Driving

2019-10-01
Felipe Codevilla , Eder Santana , Antonio M. López +1 more
Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data … Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-ofthe-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: some wellknown limitations (e.g., dataset bias and overfitting), new generalization issues (e.g., dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at http:// github.com/felipecode/coiltraine/blob/ master/docs/exploring_limitations.md.
View PDF Chat

End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit Affordances

2020-06-01
Marin Toromanoff , Émilie Wirbel , Fabien Moutarde
Reinforcement Learning (RL) aims at learning an optimal behavior policy from its own experiments and not rule-based control methods. However, there is no RL algorithm yet capable of handling a … Reinforcement Learning (RL) aims at learning an optimal behavior policy from its own experiments and not rule-based control methods. However, there is no RL algorithm yet capable of handling a task as difficult as urban driving. We present a novel technique, coined implicit affordances, to effectively leverage RL for urban driving thus including lane keeping, pedestrians and vehicles avoidance, and traffic light detection. To our knowledge we are the first to present a successful RL agent handling such a complex task especially regarding the traffic light detection. Furthermore, we have demonstrated the effectiveness of our method by winning the Camera Only track of the CARLA challenge.
View PDF Chat

Deformable part models are convolutional neural networks

2015-06-01
Ross Girshick , Forrest Iandola , Trevor Darrell +1 more
Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random … Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models (Markov random fields), while CNNs are "black-box" non-linear classifiers. In this paper, we show that a DPM can be formulated as a CNN, thus providing a synthesis of the two ideas. Our construction involves unrolling the DPM inference algorithm and mapping each step to an equivalent CNN layer. From this perspective, it is natural to replace the standard image features used in DPMs with a learned feature extractor. We call the resulting model a DeepPyramid DPM and experimentally validate it on PASCAL VOC object detection. We find that DeepPyramid DPMs significantly outperform DPMs based on histograms of oriented gradients features (HOG) and slightly outperforms a comparable version of the recently introduced R-CNN detection system, while running significantly faster.
View PDF Chat

Pedestrian Detection with Unsupervised Multi-stage Feature Learning

2013-06-01
Pierre Sermanet , Koray Kavukcuoglu , Soumith Chintala +1 more
Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all … Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we report state-of-the-art and competitive results on all major pedestrian datasets with a convolutional network model. The model uses a few new twists, such as multi-stage features, connections that skip layers to integrate global shape information with local distinctive motif information, and an unsupervised method based on convolutional sparse coding to pre-train the filters at each stage.
View PDF Chat

Label Efficient Visual Abstractions for Autonomous Driving

2020-10-24
Aseem Behl , Kashyap Chitta , Aditya Prakash +2 more
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. … It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, i.e., the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (e.g., object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.
View PDF Chat

End to End Learning for Self-Driving Cars

2016-01-01
Mariusz Bojarski , Davide Del Testa , Daniel Dworakowski +7 more
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data … We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with unclear visual guidance such as in parking lots and on unpaved roads. The system automatically learns internal representations of the necessary processing steps such as detecting useful road features with only the human steering angle as the training signal. We never explicitly trained it to detect, for example, the outline of roads. Compared to explicit decomposition of the problem, such as lane marking detection, path planning, and control, our end-to-end system optimizes all processing steps simultaneously. We argue that this will eventually lead to better performance and smaller systems. Better performance will result because the internal components self-optimize to maximize overall system performance, instead of optimizing human-selected intermediate criteria, e.g., lane detection. Such criteria understandably are selected for ease of human interpretation which doesn't automatically guarantee maximum system performance. Smaller networks are possible because the system learns to solve the problem with the minimal number of processing steps. We used an NVIDIA DevBox and Torch 7 for training and an NVIDIA DRIVE(TM) PX self-driving car computer also running Torch 7 for determining where to drive. The system operates at 30 frames per second (FPS).

Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D

2020-01-01
Jonah Philion , Sanja Fidler
View PDF Chat

Learning to Detect Vehicles by Clustering Appearance Patterns

2015-03-23
Eshed Ohn-Bar , Mohan M. Trivedi
This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual … This paper studies efficient means in dealing with intracategory diversity in object detection. Strategies for occlusion and orientation handling are explored by learning an ensemble of detection models from visual and geometrical clusters of object instances. An AdaBoost detection scheme is employed with pixel lookup features for fast detection. The analysis provides insight into the design of a robust vehicle detection system, showing promise in terms of detection performance and orientation estimation accuracy.
View PDF Chat

Convolutional Channel Features

2015-12-01
Bin Yang , Junjie Yan , Zhen Lei +1 more
Deep learning methods are powerful tools but often suffer from expensive computation and limited flexibility. An alternative is to combine light-weight models with deep representations. As successful cases exist in … Deep learning methods are powerful tools but often suffer from expensive computation and limited flexibility. An alternative is to combine light-weight models with deep representations. As successful cases exist in several visual problems, a unified framework is absent. In this paper, we revisit two widely used approaches in computer vision, namely filtered channel features and Convolutional Neural Networks (CNN), and absorb merits from both by proposing an integrated method called Convolutional Channel Features (CCF). CCF transfers low-level features from pre-trained CNN models to feed the boosting forest model. With the combination of CNN features and boosting forest, CCF benefits from the richer capacity in feature representation compared with channel features, as well as lower cost in computation and storage compared with end-to-end CNN methods. We show that CCF serves as a good way of tailoring pre-trained CNN models to diverse tasks without fine-tuning the whole network to each task by achieving state-of-the-art performances in pedestrian detection, face detection, edge detection and object proposal generation.
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

Driving Policy Transfer via Modularity and Abstraction

2018-01-01
Matthias Müller , Alexey Dosovitskiy , Bernard Ghanem +1 more
End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by providing a cheap, safe, and … End-to-end approaches to autonomous driving have high sample complexity and are difficult to scale to realistic urban driving. Simulation can help end-to-end driving systems by providing a cheap, safe, and diverse training environment. Yet training driving policies in simulation brings up the problem of transferring such policies to the real world. We present an approach to transferring driving policies from simulation to reality via modularity and abstraction. Our approach is inspired by classic driving systems and aims to combine the benefits of modular architectures and end-to-end deep learning approaches. The key idea is to encapsulate the driving policy such that it is not directly exposed to raw perceptual input or low-level vehicle dynamics. We evaluate the presented approach in simulated urban environments and in the real world. In particular, we transfer a driving policy trained in simulation to a 1/5-scale robotic truck that is deployed in a variety of conditions, with no finetuning, on two continents. The supplementary video can be viewed at https://youtu.be/BrMDJqI6H5U

OIL: Observational Imitation Learning

2019-06-22
Guohao Li , Matthias Mueller , Vincent Casser +3 more
Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an endto-end policy, which directly predicts controls from raw images.However, these approaches tend to be … Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an endto-end policy, which directly predicts controls from raw images.However, these approaches tend to be sensitive to mistakes by the teacher and do not scale well to other environments or vehicles.To this end, we propose Observational Imitation Learning (OIL), a novel imitation learning variant that supports online training and automatic selection of optimal behavior by observing multiple imperfect teachers.We apply our proposed methodology to the challenging problems of autonomous driving and UAV racing.For both tasks, we utilize the Sim4CV simulator [23] that enables the generation of large amounts of synthetic training data and also allows for online learning and evaluation.We train a perception network to predict waypoints from raw image data and use OIL to train another network to predict controls from these waypoints.Extensive experiments demonstrate that our trained network outperforms its teachers, conventional imitation learning (IL) and reinforcement learning (RL) baselines and even humans in simulation.
View PDF Chat

CARLA: An Open Urban Driving Simulator

2017-01-01
Alexey Dosovitskiy , Germán Ros , Felipe Codevilla +2 more
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In … We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support development, training, and validation of autonomous urban driving systems. In addition to open-source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specification of sensor suites and environmental conditions. We use CARLA to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end-to-end model trained via reinforcement learning. The approaches are evaluated in controlled scenarios of increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform's utility for autonomous driving research. The supplementary video can be viewed at https://youtu.be/Hp8Dz-Zek2E
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

Monocular Plan View Networks for Autonomous Driving

2019-11-01
Dequan Wang , Coline Devin , Qi-Zhi Cai +2 more
Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into … Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation of observations into a bird's eye view, also known as plan view, for end-to-end control. We detect vehicles and pedestrians in the first person view and project them into an overhead plan view. This representation provides an abstraction of the environment from which a deep network can easily deduce the positions and directions of entities. Additionally, the plan view enables us to leverage advances in 3D object detection in conjunction with deep policy learning. We evaluate our monocular plan view network on the photo-realistic Grand Theft Auto V simulator. A network using both a plan view and front view causes less than half as many collisions as previous detection-based methods and an order of magnitude fewer collisions than pure pixel-based policies.
View PDF Chat

Two-Stream Convolutional Networks for Action Recognition in Videos

2014-01-01
Karen Simonyan , Andrew Zisserman
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion … We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.

Exemplar based Deep Discriminative and Shareable Feature Learning for scene image classification

2015-02-16
Zhen Zuo , Gang Wang , Bing Shuai +2 more
View PDF Chat

Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking

2018-05-01
Sarthak Sharma , Junaid Ansari , J. Krishna Murthy +1 more
This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios. Using images from a monocular camera alone, we devise pairwise costs for object … This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios. Using images from a monocular camera alone, we devise pairwise costs for object tracks, based on several 3D cues such as object pose, shape, and motion. The proposed costs are agnostic to the data association method and can be incorporated into any optimization framework to output the pairwise data associations. These costs are easy to implement, can be computed in real-time, and complement each other to account for possible errors in a tracking-by-detection framework. We perform an extensive analysis of the designed costs and empirically demonstrate consistent improvement over the state-of-the-art under varying conditions that employ a range of object detectors, exhibit a variety in camera and object motions, and, more importantly, are not reliant on the choice of the association framework. We also show that, by using the simplest of associations frameworks (two-frame Hungarian assignment), we surpass the state-of-the-art in multi-object-tracking on road scenes. More qualitative and quantitative results can be found at https://junaidcs032.github.io/Geometry_ObjectShape_MOT/.
View PDF Chat

Deep Object-Centric Policies for Autonomous Driving

2019-05-01
Dequan Wang , Coline Devin , Qi-Zhi Cai +2 more
While learning visuomotor skills in an end-to-end manner is appealing, deep neural networks are often uninterpretable and fail in surprising ways. For robotics tasks, such as autonomous driving, models that … While learning visuomotor skills in an end-to-end manner is appealing, deep neural networks are often uninterpretable and fail in surprising ways. For robotics tasks, such as autonomous driving, models that explicitly represent objects may be more robust to new scenes and provide intuitive visualizations. We describe a taxonomy of “object-centric” models which leverage both object instances and end-to-end learning. In the Grand Theft Auto V simulator, we show that object-centric models outperform object-agnostic methods in scenes with other vehicles and pedestrians, even with an imperfect detector. We also demonstrate that our architectures perform well on real-world environments by evaluating on the Berkeley DeepDrive Video dataset, where an object-centric model outperforms object-agnostic models in the low-data regimes.
View PDF Chat

Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

2017-10-01
Zhaofan Qiu , Ting Yao , Tao Mei
Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video … Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation. A few studies have shown that performing 3D convolutions is a rewarding approach to capture both spatial and temporal dimensions in videos. However, the development of a very deep 3D CNN from scratch results in expensive computational cost and memory demand. A valid question is why not recycle off-the-shelf 2D networks for a 3D CNN. In this paper, we devise multiple variants of bottleneck building blocks in a residual learning framework by simulating 3 x 3 x 3 convolutions with 1 × 3 × 3 convolutional filters on spatial domain (equivalent to 2D CNN) plus 3 × 1 × 1 convolutions to construct temporal connections on adjacent feature maps in time. Furthermore, we propose a new architecture, named Pseudo-3D Residual Net (P3D ResNet), that exploits all the variants of blocks but composes each in different placement of ResNet, following the philosophy that enhancing structural diversity with going deep could improve the power of neural networks. Our P3D ResNet achieves clear improvements on Sports-1M video classification dataset against 3D CNN and frame-based 2D CNN by 5.3% and 1.8%, respectively. We further examine the generalization performance of video representation produced by our pre-trained P3D ResNet on five different benchmarks and three different tasks, demonstrating superior performances over several state-of-the-art techniques.
View PDF Chat

Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

2018-06-01
Roberto Cipolla , Yarin Gal , Alex Kendall
Numerous deep learning applications benefit from multitask learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent … Numerous deep learning applications benefit from multitask learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between each task's loss. Tuning these weights by hand is a difficult and expensive process, making multi-task learning prohibitive in practice. We propose a principled approach to multi-task deep learning which weighs multiple loss functions by considering the homoscedastic uncertainty of each task. This allows us to simultaneously learn various quantities with different units or scales in both classification and regression settings. We demonstrate our model learning per-pixel depth regression, semantic and instance segmentation from a monocular input image. Perhaps surprisingly, we show our model can learn multi-task weightings and outperform separate models trained individually on each task.
View PDF Chat

Anticipating Traffic Accidents with Adaptive Loss and Large-Scale Incident DB

2018-06-01
Tomoyuki Suzuki , Hirokatsu Kataoka , Yoshimitsu Aoki +1 more
In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation. The … In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation. The proposed AdaLEA allows a model to gradually learn an earlier anticipation as training progresses. The loss function adaptively assigns penalty weights depending on how early the model can anticipate a traffic accident at each epoch. Additionally, we construct a Near-miss Incident DataBase for anticipation. This database contains an enormous number of traffic near-miss incident videos and annotations for detail evaluation of two tasks, risk anticipation and risk-factor anticipation. In our experimental results, we found our proposal achieved the highest scores for risk anticipation (+6.6% better on mean average precision (mAP) and 2.36 sec earlier than previous work on the average time-to-collision (ATTC)) and risk-factor anticipation (+4.3% better on mAP and 0.70 sec earlier than previous work on ATTC).
View PDF Chat

Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras

2019-10-01
Ariel Gordon , Hanhan Li , Rico Jonschkowski +1 more
We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly … We present a novel method for simultaneous learning of depth, egomotion, object motion, and camera intrinsics from monocular videos, using only consistency across neighboring video frames as supervision signal. Similarly to prior work, our method learns by applying differentiable warping to frames and comparing the result to adjacent ones, but it provides several improvements: We address occlusions geometrically and differentiably, directly using the depth maps as predicted during training. We introduce randomized layer normalization, a novel powerful regularizer, and we account for object motion relative to the scene. To the best of our knowledge, our work is the first to learn the camera intrinsic parameters, including lens distortion, from video in an unsupervised manner, thereby allowing us to extract accurate depth and motion from arbitrary videos of unknown origin at scale. We evaluate our results on the Cityscapes, KITTI and EuRoC datasets, establishing new state of the art on depth prediction and odometry, and demonstrate qualitatively that depth prediction can be learned from a collection of YouTube videos. The code will be open sourced once anonymity is lifted.
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

What You See is What You Get: Exploiting Visibility for 3D Object Detection

2020-06-01
Peiyun Hu , Jason Ziglar , David Held +1 more
Recent advances in 3D sensing have created unique challenges for computer vision. One fundamental challenge is finding a good representation for 3D sensor data. Most popular representations (such as PointNet) … Recent advances in 3D sensing have created unique challenges for computer vision. One fundamental challenge is finding a good representation for 3D sensor data. Most popular representations (such as PointNet) are proposed in the context of processing truly 3D data (e.g. points sampled from mesh models), ignoring the fact that 3D sensored data such as a LiDAR sweep is in fact 2.5D. We argue that representing 2.5D data as collections of (x,y,z) points fundamentally destroys hidden information about freespace. In this paper, we demonstrate such knowledge can be efficiently recovered through 3D raycasting and readily incorporated into batch-based gradient learning. We describe a simple approach to augmenting voxel-based networks with visibility: we add a voxelized visibility map as an additional input stream. In addition, we show that visibility can be combined with two crucial modifications common to state-of-the-art 3D detectors: synthetic data augmentation of virtual objects and temporal aggregation of LiDAR sweeps over multiple time frames. On the NuScenes 3D detection benchmark, we show that, by adding an additional stream for visibility input, we can significantly improve the overall detection accuracy of a state-of-the-art 3D detector.
View PDF Chat

End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression

2015-06-01
Li Wan , David Eigen , Rob Fergus
Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composition, … Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composition, modeling fine-grained spatial relationships between parts; likewise, ConvNets are adept at producing powerful image features, having been discriminatively trained directly on the pixels. In this paper, we propose a new model that combines these two approaches, obtaining the advantages of each. We train this model using a new structured loss function that considers all bounding boxes within an image, rather than isolated object instances. This enables the non-maximal suppression (NMS) operation, previously treated as a separate post-processing stage, to be integrated into the model. This allows for discriminative training of our combined Convnet + DPM + NMS model in end-to-end fashion. We evaluate our system on PASCAL VOC 2007 and 2011 datasets, achieving competitive results on both benchmarks.
View PDF Chat

Path Planning in Dynamic Environments with Adaptive Dimensionality.

2016-01-01
Anirudh Vemula , Katharina Mülling , Jean Oh

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

2018-06-01
Agrim Gupta , Justin Johnson , Li Fei-Fei +2 more
Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is … Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.
View PDF Chat

A Baseline for 3D Multi-Object Tracking

2019-07-09
Xinshuo Weng , Kris Kitani
3D multi-object tracking (MOT) is an essential component technology for many real-time applications such as autonomous driving or assistive robotics. However, recent works for 3D MOT tend to focus more … 3D multi-object tracking (MOT) is an essential component technology for many real-time applications such as autonomous driving or assistive robotics. However, recent works for 3D MOT tend to focus more on developing accurate systems giving less regard to computational cost and system complexity. In contrast, this work proposes a simple yet accurate real-time baseline 3D MOT system. We use an off-the-shelf 3D object detector to obtain oriented 3D bounding boxes from the LiDAR point cloud. Then, a combination of 3D Kalman filter and Hungarian algorithm is used for state estimation and data association. Although our baseline system is a straightforward combination of standard methods, we obtain the state-of-the-art results. To evaluate our baseline system, we propose a new 3D MOT extension to the official KITTI 2D MOT evaluation along with two new metrics. Our proposed baseline method for 3D MOT establishes new state-of-the-art performance on 3D MOT for KITTI, improving the 3D MOTA from 72.23 of prior art to 76.47. Surprisingly, by projecting our 3D tracking results to the 2D image plane and compare against published 2D MOT methods, our system places 2nd on the official KITTI leaderboard. Also, our proposed 3D MOT method runs at a rate of 214.7 FPS, 65 times faster than the state-of-the-art 2D MOT system. Our code is publicly available at this https URL

Going deeper with convolutions

2015-06-01
Christian Szegedy , Wei Liu , Yangqing Jia +6 more
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 … We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
View PDF Chat

Beyond short snippets: Deep networks for video classification

2015-06-01
Joe Yue-Hei Ng , Matthew Hausknecht , Sudheendra Vijayanarasimhan +3 more
Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep … Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep neural network architectures to combine image information across a video over longer time periods than previously attempted. We propose two methods capable of handling full length videos. The first method explores various convolutional temporal feature pooling architectures, examining the various design choices which need to be made when adapting a CNN for this task. The second proposed method explicitly models the video as an ordered sequence of frames. For this purpose we employ a recurrent neural network that uses Long Short-Term Memory (LSTM) cells which are connected to the output of the underlying CNN. Our best networks exhibit significant performance improvements over previously published results on the Sports 1 million dataset (73.1% vs. 60.9%) and the UCF-101 datasets with (88.6% vs. 88.0%) and without additional optical flow information (82.6% vs. 73.0%).
View PDF Chat

Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision

2018-03-01
Xinshuo Weng , Shangxuan Wu , Fares Beainy +1 more
Across most pedestrian detection datasets, it is typically assumed that pedestrians will be standing upright with respect to the image coordinate system. This assumption is not always valid for many … Across most pedestrian detection datasets, it is typically assumed that pedestrians will be standing upright with respect to the image coordinate system. This assumption is not always valid for many vision-equipped mobile platforms, such as mobile phones, UAVs, or construction vehicles on rugged terrain. In these situations, the motion of the camera can cause images of pedestrians to be captured at extreme angles. This can lead to inferior pedestrian detection performance when using standard pedestrian detectors. To address this issue, we propose a Rotational Rectification Network (R2N) that can be inserted into any CNNbased pedestrian (or object) detector to adapt it to significant changes in camera rotation. The rotational rectification network uses a 2D rotation estimation module that passes rotational information to a spatial transformer network [12] to undistort image features. To enable robust rotation estimation, we propose a Global Polar Pooling (GPPooling) operator to capture rotational shifts in convolutional features. Through our experiments, we show how our rotational rectification network can be used to improve the performance of state-of-the-art pedestrian detectors under heavy image rotation by up to 45%.
View PDF Chat

CIRL: Controllable Imitative Reinforcement Learning for Vision-Based Self-driving

2018-01-01
Xiaodan Liang , Tairui Wang , Luona Yang +1 more
View PDF Chat

YOLOv3: An Incremental Improvement.

2018-04-08
Joseph Redmon , Ali Farhadi
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little … We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at this https URL

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.

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading

2019-01-01
Xinshuo Weng , Kris Kitani
We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural … We focus on the word-level visual lipreading, which requires recognizing the word being spoken, given only the video but not the audio. State-of-the-art methods explore the use of end-to-end neural networks, including a shallow (up to three layers) 3D convolutional neural network (CNN) + a deep 2D CNN (e.g., ResNet) as the front-end to extract visual features, and a recurrent neural network (e.g., bidirectional LSTM) as the back-end for classification. In this work, we propose to replace the shallow 3D CNNs + deep 2D CNNs front-end with recent successful deep 3D CNNs --- two-stream (i.e., grayscale video and optical flow streams) I3D. We evaluate different combinations of front-end and back-end modules with the grayscale video and optical flow inputs on the LRW dataset. The experiments show that, compared to the shallow 3D CNNs + deep 2D CNNs front-end, the deep 3D CNNs front-end with pre-training on the large-scale image and video datasets (e.g., ImageNet and Kinetics) can improve the classification accuracy. Also, we demonstrate that using the optical flow input alone can achieve comparable performance as using the grayscale video as input. Moreover, the two-stream network using both the grayscale video and optical flow inputs can further improve the performance. Overall, our two-stream I3D front-end with a Bi-LSTM back-end results in an absolute improvement of 5.3% over the previous art on the LRW dataset.

ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst

2019-06-22
Mayank Bansal , Alex Krizhevsky , Abhijit S. Ogale
Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle.We find that standard behavior cloning is insufficient for … Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle.We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough.We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road.Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -the perturbations then provide an important signal for these losses and lead to robustness of the learned model.We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors.Finally, we demonstrate the model driving a real car at our test facility.
View PDF Chat

Learning Spatiotemporal Features with 3D Convolutional Networks

2015-12-01
Du Tran , Lubomir Bourdev , Rob Fergus +2 more
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: … We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets, 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets, and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.
View PDF Chat

Simple online and realtime tracking

2016-08-17
Alex Bewley , Zongyuan Ge , Lionel Ott +2 more
This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is … This paper explores a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and realtime applications. To this end, detection quality is identified as a key factor influencing tracking performance, where changing the detector can improve tracking by up to 18.9%. Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers. Furthermore, due to the simplicity of our tracking method, the tracker updates at a rate of 260 Hz which is over 20x faster than other state-of-the-art trackers.
View PDF Chat

Spatiotemporal Residual Networks for Video Action Recognition

2016-01-01
Christoph Feichtenhofer , Axel Pinz , Richard P. Wildes
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In … Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos. Recently, Residual Networks (ResNets) have arisen as a new technique to train extremely deep architectures. In this paper, we introduce spatiotemporal ResNets as a combination of these two approaches. Our novel architecture generalizes ResNets for the spatiotemporal domain by introducing residual connections in two ways. First, we inject residual connections between the appearance and motion pathways of a two-stream architecture to allow spatiotemporal interaction between the two streams. Second, we transform pretrained image ConvNets into spatiotemporal networks by equipping these with learnable convolutional filters that are initialized as temporal residual connections and operate on adjacent feature maps in time. This approach slowly increases the spatiotemporal receptive field as the depth of the model increases and naturally integrates image ConvNet design principles. The whole model is trained end-to-end to allow hierarchical learning of complex spatiotemporal features. We evaluate our novel spatiotemporal ResNet using two widely used action recognition benchmarks where it exceeds the previous state-of-the-art.

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

2010-11-02
Stéphane Ross , Geoffrey J. Gordon , J. Andrew Bagnell
Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in … Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting. We show that any such no regret algorithm, combined with additional reduction assumptions, must find a policy with good performance under the distribution of observations it induces in such sequential settings. We demonstrate that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

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.

Aggregate channel features for multi-view face detection

2014-09-01
Bin Yang , Junjie Yan , Zhen Lei +1 more
Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the … Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones. While many subsequences have improved the work with more powerful learning algorithms, the feature representation used for face detection still can't meet the demand for effectively and efficiently handling faces with large appearance variance in the wild. To solve this bottleneck, we borrow the concept of channel features to the face detection domain, which extends the image channel to diverse types like gradient magnitude and oriented gradient histograms and therefore encodes rich information in a simple form. We adopt a novel variant called aggregate channel features, make a full exploration of feature design, and discover a multi-scale version of features with better performance. To deal with poses of faces in the wild, we propose a multi-view detection approach featuring score re-ranking and detection adjustment. Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images.
View PDF Chat

Cognitive Mapping and Planning for Visual Navigation

2017-07-01
Saurabh Gupta , James Davidson , Sergey Levine +2 more
We introduce a neural architecture for navigation in novel environments. Our proposed architecture learns to map from first-person views and plans a sequence of actions towards goals in the environment. … We introduce a neural architecture for navigation in novel environments. Our proposed architecture learns to map from first-person views and plans a sequence of actions towards goals in the environment. The Cognitive Mapper and Planner (CMP) is based on two key ideas: a) a unified joint architecture for mapping and planning, such that the mapping is driven by the needs of the planner, and b) a spatial memory with the ability to plan given an incomplete set of observations about the world. CMP constructs a top-down belief map of the world and applies a differentiable neural net planner to produce the next action at each time step. The accumulated belief of the world enables the agent to track visited regions of the environment. Our experiments demonstrate that CMP outperforms both reactive strategies and standard memory-based architectures and performs well in novel environments. Furthermore, we show that CMP can also achieve semantically specified goals, such as "go to a chair".
View PDF Chat