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

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in Vitro

2017-10-01
Zhedong Zheng , Liang Zheng , Yi Yang
The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain … The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/ Person-reID_GAN.
View PDF Chat

A Discriminatively Learned CNN Embedding for Person Reidentification

2017-12-13
Zhedong Zheng , Liang Zheng , Yi Yang
We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss … We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e, verification and classification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a new siamese network that simultaneously computes identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the annotations. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.
View PDF Chat

Improving person re-identification by attribute and identity learning

2019-06-06
Yutian Lin , Liang Zheng , Zhedong Zheng +4 more
View PDF Chat

Joint Discriminative and Generative Learning for Person Re-Identification

2019-06-01
Zhedong Zheng , Xiaodong Yang , Zhiding Yu +3 more
Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance … Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.
View PDF Chat

Camera Style Adaptation for Person Re-identification

2018-06-01
Zhun Zhong , Liang Zheng , Zhedong Zheng +2 more
Being a cross-camera retrieval task, person re-identification suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this … Being a cross-camera retrieval task, person re-identification suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation. CamStyle can serve as a data augmentation approach that smooths the camera style disparities. Specifically, with CycleGAN, labeled training images can be style-transferred to each camera, and, along with the original training samples, form the augmented training set. This method, while increasing data diversity against over-fitting, also incurs a considerable level of noise. In the effort to alleviate the impact of noise, the label smooth regularization (LSR) is adopted. The vanilla version of our method (without LSR) performs reasonably well on few-camera systems in which over-fitting often occurs. With LSR, we demonstrate consistent improvement in all systems regardless of the extent of over-fitting. We also report competitive accuracy compared with the state of the art. Code is available at: https://github.com/zhunzhong07/CamStyle.
View PDF Chat

Pedestrian Alignment Network for Large-scale Person Re-Identification

2018-10-04
Zhedong Zheng , Liang Zheng , Yi Yang
Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually … Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images. However, this process suffers from two types of detector errors: excessive background and part missing. Both errors deteriorate the quality of pedestrian alignment and may compromise pedestrian matching due to the position and scale variances. To address the misalignment problem, we propose that alignment can be learned from an identification procedure. We introduce the pedestrian alignment network (PAN) which allows discriminative embedding learning and pedestrian alignment without extra annotations. Our key observation is that when the convolutional neural network (CNN) learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background. The proposed network thus takes advantage of this attention mechanism to adaptively locate and align pedestrians within a bounding box. Visual examples show that pedestrians are better aligned with PAN. Experiments on three large-scale re-ID datasets confirm that PAN improves the discriminative ability of the feature embeddings and yields competitive accuracy with the state-of-the-art methods.
View PDF Chat

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

2021-01-06
Zhedong Zheng , Yi Yang
View PDF Chat

Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification

2018-01-01
Qingji Guan , Yaping Huang , Zhun Zhong +3 more
This paper considers the task of thorax disease classification on chest X-ray images. Existing methods generally use the global image as input for network learning. Such a strategy is limited … This paper considers the task of thorax disease classification on chest X-ray images. Existing methods generally use the global image as input for network learning. Such a strategy is limited in two aspects. 1) A thorax disease usually happens in (small) localized areas which are disease specific. Training CNNs using global image may be affected by the (excessive) irrelevant noisy areas. 2) Due to the poor alignment of some CXR images, the existence of irregular borders hinders the network performance. In this paper, we address the above problems by proposing a three-branch attention guided convolution neural network (AG-CNN). AG-CNN 1) learns from disease-specific regions to avoid noise and improve alignment, 2) also integrates a global branch to compensate the lost discriminative cues by local branch. Specifically, we first learn a global CNN branch using global images. Then, guided by the attention heat map generated from the global branch, we inference a mask to crop a discriminative region from the global image. The local region is used for training a local CNN branch. Lastly, we concatenate the last pooling layers of both the global and local branches for fine-tuning the fusion branch. The Comprehensive experiment is conducted on the ChestX-ray14 dataset. We first report a strong global baseline producing an average AUC of 0.841 with ResNet-50 as backbone. After combining the local cues with the global information, AG-CNN improves the average AUC to 0.868. While DenseNet-121 is used, the average AUC achieves 0.871, which is a new state of the art in the community.
View PDF Chat

Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

2017-01-01
Zhedong Zheng , Liang Zheng , Yi Yang
The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain … The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/Person-reID_GAN.
View PDF Chat

University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization

2020-10-12
Zhedong Zheng , Yunchao Wei , Yi Yang
We consider the problem of cross-view geo-localization. The primary challenge is to learn the robust feature against large viewpoint changes. Existing benchmarks can help, but are limited in the number … We consider the problem of cross-view geo-localization. The primary challenge is to learn the robust feature against large viewpoint changes. Existing benchmarks can help, but are limited in the number of viewpoints. Image pairs, containing two viewpoints, e.g., satellite and ground, are usually provided, which may compromise the feature learning. Besides phone cameras and satellites, in this paper, we argue that drones could serve as the third platform to deal with the geo-localization problem. In contrast to traditional ground-view images, drone-view images meet fewer obstacles, e.g., trees, and provide a comprehensive view when flying around the target place. To verify the effectiveness of the drone platform, we introduce a new multi-view multi-source benchmark for drone-based geo-localization, named University-1652. University-1652 contains data from three platforms, i.e., synthetic drones, satellites and ground cameras of 1,652 university buildings around the world. To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i.e., drone-view target localization and drone navigation. As the name implies, drone-view target localization intends to predict the location of the target place via drone-view images. On the other hand, given a satellite-view query image, drone navigation is to drive the drone to the area of interest in the query. We use this dataset to analyze a variety of off-the-shelf CNN features and propose a strong CNN baseline on this challenging dataset. The experiments show that University-1652 helps the model to learn viewpoint-invariant features and also has good generalization ability in real-world scenarios.
View PDF Chat

Macro-Micro Adversarial Network for Human Parsing

2018-01-01
Yawei Luo , Zhedong Zheng , Liang Zheng +3 more
View PDF Chat

VehicleNet: Learning Robust Visual Representation for Vehicle Re-Identification

2020-08-07
Zhedong Zheng , Tao Ruan , Yunchao Wei +2 more
One fundamental challenge of vehicle re-identification (re-id) is to learn robust and discriminative visual representation, given the significant intra-class vehicle variations across different camera views. As the existing vehicle datasets … One fundamental challenge of vehicle re-identification (re-id) is to learn robust and discriminative visual representation, given the significant intra-class vehicle variations across different camera views. As the existing vehicle datasets are limited in terms of training images and viewpoints, we propose to build a unique large-scale vehicle dataset (called VehicleNet) by harnessing four public vehicle datasets, and design a simple yet effective two-stage progressive approach to learning more robust visual representation from VehicleNet. The first stage of our approach is to learn the generic representation for all domains (i.e., source vehicle datasets) by training with the conventional classification loss. This stage relaxes the full alignment between the training and testing domains, as it is agnostic to the target vehicle domain. The second stage is to fine-tune the trained model purely based on the target vehicle set, by minimizing the distribution discrepancy between our VehicleNet and any target domain. We discuss our proposed multi-source dataset VehicleNet and evaluate the effectiveness of the two-stage progressive representation learning through extensive experiments. We achieve the state-of-art accuracy of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{86.07}\%$</tex-math></inline-formula> mAP on the private test set of AICity Challenge, and competitive results on two other public vehicle re-id datasets, i.e., VeRi-776 and VehicleID. We hope this new VehicleNet dataset and the learned robust representations can pave the way for vehicle re-id in the real-world environments.
View PDF Chat

Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization

2021-02-23
Tingyu Wang , Zhedong Zheng , Chenggang Yan +4 more
Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by … Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations. Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas. In this work, we argue that neighbor areas can be leveraged as auxiliary information, enriching discriminative clues for geolocalization. Specifically, we introduce a simple and effective deep neural network, called Local Pattern Network (LPN), to take advantage of contextual information in an end-to-end manner. Without using extra part estimators, LPN adopts a square-ring feature partition strategy, which provides the attention according to the distance to the image center. It eases the part matching and enables the part-wise representation learning. Owing to the square-ring partition design, the proposed LPN has good scalability to rotation variations and achieves competitive results on three prevailing benchmarks, i.e., University-1652, CVUSA and CVACT. Besides, we also show the proposed LPN can be easily embedded into other frameworks to further boost performance.
View PDF Chat

Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification

2018-10-08
Yan Huang , Jingsong Xu , Qiang Wu +3 more
Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images, the amount of available training data … Sufficient training data normally is required to train deeply learned models. However, due to the expensive manual process for labelling large number of images, the amount of available training data is always limited. To produce more data for training a deep network, Generative Adversarial Network (GAN) can be used to generate artificial sample data. However, the generated data usually does not have annotation labels. To solve this problem, in this paper, we propose a virtual label called Multi-pseudo Regularized Label (MpRL) and assign it to the generated data. With MpRL, the generated data will be used as the supplementary of real training data to train a deep neural network in a semi-supervised learning fashion. To build the corresponding relationship between the real data and generated data, MpRL assigns each generated data a proper virtual label which reflects the likelihood of the affiliation of the generated data to pre-defined training classes in the real data domain. Unlike the traditional label which usually is a single integral number, the virtual label proposed in this work is a set of weight-based values each individual of which is a number in (0,1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data. A comprehensive evaluation is carried out by adopting two state-of-the-art convolutional neural networks (CNNs) in our experiments to verify the effectiveness of MpRL. Experiments demonstrate that by assigning MpRL to generated data, we can further improve the person re-ID performance on five re-ID datasets, i.e., Market-1501, DukeMTMC-reID, CUHK03, VIPeR, and CUHK01. The proposed method obtains +6.29%, +6.30%, +5.58%, +5.84%, and +3.48% improvements in rank-1 accuracy over a strong CNN baseline on the five datasets respectively, and outperforms state-of-the-art methods.
View PDF Chat

Dual-path Convolutional Image-Text Embeddings with Instance Loss

2020-05-22
Zhedong Zheng , Liang Zheng , Michael Garrett +3 more
Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual … Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image / text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss is hard for network learning, since it starts from the two heterogeneous features to build inter-modal relationship. To address this problem, we propose the instance loss which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image / text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this paper constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.
View PDF Chat

Unsupervised Scene Adaptation with Memory Regularization in vivo

2020-07-01
Zhedong Zheng , Yi Yang
This work focuses on the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing approaches focus on minoring the inter-domain gap between the … This work focuses on the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing approaches focus on minoring the inter-domain gap between the source and target domains. However, the intra-domain knowledge and inherent uncertainty learned by the network are under-explored. In this paper, we propose an orthogonal method, called memory regularization in vivo, to exploit the intra-domain knowledge and regularize the model training. Specifically, we refer to the segmentation model itself as the memory module, and minor the discrepancy of the two classifiers, i.e., the primary classifier and the auxiliary classifier, to reduce the prediction inconsistency. Without extra parameters, the proposed method is complementary to most existing domain adaptation methods and could generally improve the performance of existing methods. Albeit simple, we verify the effectiveness of memory regularization on two synthetic-to-real benchmarks: GTA5 → Cityscapes and SYNTHIA → Cityscapes, yielding +11.1% and +11.3% mIoU improvement over the baseline model, respectively. Besides, a similar +12.0% mIoU improvement is observed on the cross-city benchmark: Cityscapes → Oxford RobotCar.
View PDF Chat

Joint Discriminative and Generative Learning for Person Re-identification

2019-01-01
Zhedong Zheng , Xiaodong Yang , Zhiding Yu +3 more
Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance … Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.
View PDF Chat

Parameter-Efficient Person Re-Identification in the 3D Space

2022-11-04
Zhedong Zheng , Xiaohan Wang , Nenggan Zheng +1 more
People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In … People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient Omni-scale Graph Network (OG-Net) to learn the pedestrian representation directly from 3D point clouds. OG-Net effectively exploits the local information provided by sparse 3D points and takes advantage of the structure and appearance information in a coherent manner. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space. We demonstrate through extensive experiments that the proposed method (1) eases the matching difficulty in the traditional 2D space, (2) exploits the complementary information of 2D appearance and 3D structure, (3) achieves competitive results with limited parameters on four large-scale person re-id datasets, and (4) has good scalability to unseen datasets. Our code, models and generated 3D human data are publicly available at https://github.com/layumi/person-reid-3d .
View PDF Chat

Dual-Path Convolutional Image-Text Embedding.

2017-11-15
Zhedong Zheng , Liang Zheng , Michael Garrett +2 more
This paper considers the task of matching images and sentences. The challenge consists in discriminatively embedding the two modalities onto a shared visual-textual space. Existing work in this field largely … This paper considers the task of matching images and sentences. The challenge consists in discriminatively embedding the two modalities onto a shared visual-textual space. Existing work in this field largely uses Recurrent Neural Networks (RNN) for text feature learning and employs off-the-shelf Convolutional Neural Networks (CNN) for image feature extraction. Our system, in comparison, differs in two key aspects. Firstly, we build a convolutional network amenable for fine-tuning the visual and textual representations, where the entire network only contains four components, i.e., convolution layer, pooling layer, rectified linear unit function (ReLU), and batch normalisation. End-to-end learning allows the system to directly learn from the data and fully utilise the supervisions. Secondly, we propose instance loss according to viewing each multimodal data pair as a class. This works with a large margin objective to learn the inter-modal correspondence between images and their textual descriptions. Experiments on two generic retrieval datasets (Flickr30k and MSCOCO) demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language person retrieval, we improve the state of the art by a large margin. Code is available at this https URL com/layumi/Image-Text-Embedding

Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark

2023-10-26
Shuyu Yang , Yinan Zhou , Zhedong Zheng +3 more
In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and … In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 × larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96 %, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/APTM.
View PDF Chat

Progressive Local Filter Pruning for Image Retrieval Acceleration

2023-01-01
Xiaodong Wang , Zhedong Zheng , Yang He +3 more
This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the … This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the model inference, which should be taken into consideration in real-world practice. The challenge of pruning image retrieval models is that the middle-level feature should be preserved as much as possible. Such different requirements of the retrieval and classification model make the traditional pruning methods not that suitable for our task. To solve the problem, we propose a new Progressive Local Filter Pruning (PLFP) method for image retrieval acceleration. Specifically, layer by layer, we analyze the local geometric properties of each filter and select the one that can be replaced by the neighbors. Then we progressively prune the filter by gradually changing the filter weights. In this way, the representation ability of the model is preserved. To verify this, we evaluate our method on two widely-used image retrieval datasets,i.e., Oxford5k and Paris6K, and one person re-identification dataset,i.e., Market-1501. The proposed method arrives with superior performance to the conventional pruning methods, suggesting the effectiveness of the proposed method for image retrieval.
View PDF Chat

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

2021-05-18
Chuchu Han , Zhedong Zheng , Changxin Gao +2 more
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and … The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.
View PDF Chat

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis

2022-06-01
Xuanmeng Zhang , Zhedong Zheng , Daiheng Gao +3 more
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail … 3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.
View PDF Chat

PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation

2023-10-26
Mu Chen , Zhedong Zheng , Yi Yang +1 more
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., … Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an image, remains under-explored. In an attempt to fill this gap, we revisit the current pixel contrast in semantic segmentation and propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts. The proposed framework exploits the inherent structures of intra-domain images, which: (1) explicitly encourages learning the discriminative pixel-wise features with intra-class compactness and inter-class separability, and (2) motivates the robust feature learning of the identical patch against different contexts or fluctuations. Extensive experiments verify the effectiveness of the proposed method, which obtains competitive accuracy on the two widely-used UDA benchmarks, e.g., 75.6 mIoU on GTA→Cityscapes and 68.2 mIoU on Synthia→Cityscapes. Moreover, our method is compatible with other UDA approaches to further improve the performance without introducing extra parameters.
View PDF Chat

Connecting Language and Vision for Natural Language-Based Vehicle Retrieval

2021-06-01
Shuai Bai , Zhedong Zheng , Xiaohan Wang +5 more
Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing prac-tices focus on the image-based vehicle matching, including vehicle re-identification and … Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing prac-tices focus on the image-based vehicle matching, including vehicle re-identification and vehicle tracking. In this paper, we apply one new modality, i.e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario. The natural language-based vehicle search poses one new challenge of fine-grained understanding of both vision and language modalities. To connect language and vision, we propose to jointly train the state-of-the-art vision models with the transformer-based language model in an end-to-end manner. Except for the network structure design and the training strategy, several optimization objectives are also revisited in this work. The qualitative and quantitative experiments verify the effectiveness of the proposed method. Our proposed method has achieved the 1st place on the 5th AI City Challenge, yielding competitive performance 18.69% MRR accuracy on the private test set. We hope this work can pave the way for the future study on using language description effectively and efficiently for real-world vehicle retrieval systems. The code will be available at https://github.com/ShuaiBai623/AIC2021-T5-CLV.
View PDF Chat

SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on

2022-01-01
Bingwen Hu , Ping Liu , Zhedong Zheng +1 more
Image-based virtual try-on is challenging in fitting a target in-shop clothes onto a reference person under diverse human poses. Previous works focus on preserving clothing details ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> … Image-based virtual try-on is challenging in fitting a target in-shop clothes onto a reference person under diverse human poses. Previous works focus on preserving clothing details ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> texture, logos, patterns) when transferring desired clothes onto a target person under a fixed pose. However, the performances of existing methods significantly dropped when extending existing methods to multi-pose virtual try-on. In this paper, we propose an end-to-end Semantic Prediction Guidance multi-pose Virtual Try-On Network (SPG-VTON), which can fit the desired clothing into a reference person under arbitrary poses. Specifically, SPG-VTON is composed of three sub-modules. First, a Semantic Prediction Module (SPM) generates the desired semantic map. The predicted semantic map provides more abundant guidance to locate the desired clothing region and produce a coarse try-on image. Second, a Clothes Warping Module (CWM) warps in-shop clothes to the desired shape according to the predicted semantic map and the desired pose. Specifically, we introduce a conductible cycle consistency loss to alleviate the misalignment in the clothing warping process. Third, a Try-on Synthesis Module (TSM) combines the coarse result and the warped clothes to generate the final virtual try-on image, preserving details of the desired clothes and under the desired pose. In addition, we introduce a face identity loss to refine the facial appearance and maintain the identity of the final virtual try-on result at the same time. We evaluate the proposed method on the most massive multi-pose dataset (MPV) and the DeepFashion dataset. The qualitative and quantitative experiments show that SPG-VTON is superior to the state-of-the-art methods and is robust to data noise, including background and accessory changes, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , hats and handbags, showing good scalability to the real-world scenario.
View PDF Chat

Open Set Adversarial Examples

2018-09-07
Zhedong Zheng , Liang Zheng , Zhilan Hu +1 more

Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes

2022-09-14
Chao Sun , Zhedong Zheng , Xiaohan Wang +2 more
The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning … The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MD</b> ), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning to separate the inputs from the mixed shape. We leverage this reconstruction task as the pretext optimization objective for self-supervised learning. There are two primary advantages: 1) Compared to prevailing image datasets, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , ImageNet, point cloud datasets are <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">de facto</i> small. The mixing process can provide a much larger online training sample pool. 2) On the other hand, the disentangling process motivates the model to mine the geometric prior knowledge, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , key points. To verify the effectiveness of the proposed pretext task, we build one baseline network, which is composed of one encoder and one decoder. During pre-training, we mix two original shapes and obtain the geometry-aware embedding from the encoder, then an instance-adaptive decoder is applied to recover the original shapes from the embedding. Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks. The proposed method has improved the empirical performance on both ModelNet-40 and ShapeNet-Part datasets in terms of point cloud classification and segmentation tasks. We further conduct ablation studies to explore the effect of each component and verify the generalization of our proposed strategy by harnessing different backbones.
View PDF Chat

Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective

2020-01-01
Xuanmeng Zhang , Minyue Jiang , Zhedong Zheng +3 more
The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw … The re-ranking approach leverages high-confidence retrieved samples to refine retrieval results, which have been widely adopted as a post-processing tool for image retrieval tasks. However, we notice one main flaw of re-ranking, i.e., high computational complexity, which leads to an unaffordable time cost for real-world applications. In this paper, we revisit re-ranking and demonstrate that re-ranking can be reformulated as a high-parallelism Graph Neural Network (GNN) function. In particular, we divide the conventional re-ranking process into two phases, i.e., retrieving high-quality gallery samples and updating features. We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph. In practice, GNN only needs to concern vertices with the connected edges. Since the graph is sparse, we can efficiently update the vertex features. On the Market-1501 dataset, we accelerate the re-ranking processing from 89.2s to 9.4ms with one K40m GPU, facilitating the real-time post-processing. Similarly, we observe that our method achieves comparable or even better retrieval results on the other four image retrieval benchmarks, i.e., VeRi-776, Oxford-5k, Paris-6k and University-1652, with limited time cost. Our code is publicly available.

Adaptive Boosting for Domain Adaptation: Toward Robust Predictions in Scene Segmentation

2022-01-01
Zhedong Zheng , Yi Yang
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, <i>i.e</i>., target domain. One common practice is to train the model on both … Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, <i>i.e</i>., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines deep model learning with the conventional training strategy, <i>i.e</i>., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate &#x201C;weak&#x201D; models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks.
View PDF Chat

Unsupervised Eyeglasses Removal in the Wild

2020-06-08
Bingwen Hu , Zhedong Zheng , Ping Liu +2 more
Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses, and sunglasses, and recovering appropriate eyes. Due to the significant visual variants, the conventional methods … Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses, and sunglasses, and recovering appropriate eyes. Due to the significant visual variants, the conventional methods lack scalability. Most existing works focus on the frontal face images in the controlled environment, such as the laboratory, and need to design specific systems for different eyeglass types. To address the limitation, we propose a unified eyeglass removal model called the eyeglasses removal generative adversarial network (ERGAN), which could handle different types of glasses in the wild. The proposed method does not depend on the dense annotation of eyeglasses location but benefits from the large-scale face images with weak annotations. Specifically, we study the two relevant tasks simultaneously, that is, removing eyeglasses and wearing eyeglasses. Given two face images with and without eyeglasses, the proposed model learns to swap the eye area in two faces. The generation mechanism focuses on the eye area and invades the difficulty of generating a new face. In the experiment, we show the proposed method achieves a competitive removal quality in terms of realism and diversity. Furthermore, we evaluate ERGAN on several subsequent tasks, such as face verification and facial expression recognition. The experiment shows that our method could serve as a preprocessing method for these tasks.
View PDF Chat

Multiple-environment Self-adaptive Network for aerial-view geo-localization

2024-03-12
Tingyu Wang , Zhedong Zheng , Yaoqi Sun +3 more
View PDF Chat

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

2020-01-01
Zhedong Zheng , Yi Yang
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard … This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground truth to fully exploit the unlabeled target-domain data. Yet the pseudo labels of the target-domain data are usually predicted by the model trained on the source domain. Thus, the generated labels inevitably contain the incorrect prediction due to the discrepancy between the training domain and the test domain, which could be transferred to the final adapted model and largely compromises the training process. To overcome the problem, this paper proposes to explicitly estimate the prediction uncertainty during training to rectify the pseudo label learning for unsupervised semantic segmentation adaptation. Given the input image, the model outputs the semantic segmentation prediction as well as the uncertainty of the prediction. Specifically, we model the uncertainty via the prediction variance and involve the uncertainty into the optimization objective. To verify the effectiveness of the proposed method, we evaluate the proposed method on two prevalent synthetic-to-real semantic segmentation benchmarks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, as well as one cross-city benchmark, i.e., Cityscapes -> Oxford RobotCar. We demonstrate through extensive experiments that the proposed approach (1) dynamically sets different confidence thresholds according to the prediction variance, (2) rectifies the learning from noisy pseudo labels, and (3) achieves significant improvements over the conventional pseudo label learning and yields competitive performance on all three benchmarks.

Behavioral Intention Prediction in Driving Scenes: A Survey

2022-01-01
Jianwu Fang , Fan Wang , Peining Shen +3 more
In the driving scene, the road agents usually conduct frequent interactions and intention understanding of the surroundings. Ego-agent (each road agent itself) predicts what behavior will be engaged by other … In the driving scene, the road agents usually conduct frequent interactions and intention understanding of the surroundings. Ego-agent (each road agent itself) predicts what behavior will be engaged by other road users all the time and expects a shared and consistent understanding for safe movement. Behavioral Intention Prediction (BIP) simulates such a human consideration process and fulfills the early prediction of specific behaviors. Similar to other prediction tasks, such as trajectory prediction, data-driven deep learning methods have taken the primary pipeline in research. The rapid development of BIP inevitably leads to new issues and challenges. To catalyze future research, this work provides a comprehensive review of BIP from the available datasets, key factors and challenges, pedestrian-centric and vehicle-centric BIP approaches, and BIP-aware applications. Based on the investigation, data-driven deep learning approaches have become the primary pipelines. The behavioral intention types are still monotonous in most current datasets and methods (e.g., Crossing (C) and Not Crossing (NC) for pedestrians and Lane Changing (LC) for vehicles) in this field. In addition, for the safe-critical scenarios (e.g., near-crashing situations), current research is limited. Through this investigation, we identify open issues in behavioral intention prediction and suggest possible insights for future research.
View PDF Chat

Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization

2022-01-01
Tingyu Wang , Zhedong Zheng , Zunjie Zhu +3 more
Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance … Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance between one embedding with others in the feature space, while neglecting the redundancy of the embedding itself. In this paper, we argue that the low redundancy is also of importance, which motivates the model to mine more diverse patterns. To verify this point, we introduce a simple yet effective regularization, i.e., Dynamic Weighted Decorrelation Regularization (DWDR), to explicitly encourage networks to learn independent embedding channels. As the name implies, DWDR regresses the embedding correlation coefficient matrix to a sparse matrix, i.e., the identity matrix, with dynamic weights. The dynamic weights are applied to focus on still correlated channels during training. Besides, we propose a cross-view symmetric sampling strategy, which keeps the example balance between different platforms. Albeit simple, the proposed method has achieved competitive results on three large-scale benchmarks, i.e., University-1652, CVUSA and CVACT. Moreover, under the harsh circumstance, e.g., the extremely short feature of 64 dimensions, the proposed method surpasses the baseline model by a clear margin.

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

2022-01-01
Yiyang Chen , Zhedong Zheng , Wei Ji +2 more
We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the … We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the latter, i.e., fine-grained search, by harnessing positive and negative pairs during training. This pair-based paradigm only considers the one-to-one distance between a pair of specific points, which is not aligned with the one-to-many coarse-grained retrieval process and compromises the recall rate. In an attempt to fill this gap, we introduce a unified learning approach to simultaneously modeling the coarse- and fine-grained retrieval by considering the multi-grained uncertainty. The key idea underpinning the proposed method is to integrate fine- and coarse-grained retrieval as matching data points with small and large fluctuations, respectively. Specifically, our method contains two modules: uncertainty modeling and uncertainty regularization. (1) The uncertainty modeling simulates the multi-grained queries by introducing identically distributed fluctuations in the feature space. (2) Based on the uncertainty modeling, we further introduce uncertainty regularization to adapt the matching objective according to the fluctuation range. Compared with existing methods, the proposed strategy explicitly prevents the model from pushing away potential candidates in the early stage, and thus improves the recall rate. On the three public datasets, i.e., FashionIQ, Fashion200k, and Shoes, the proposed method has achieved +4.03%, +3.38%, and +2.40% Recall@50 accuracy over a strong baseline, respectively.
View PDF Chat

Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation

2024-02-16
Yucheng Suo , Zhedong Zheng , Xiaohan Wang +2 more
Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate … Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate user photos using sign language videos of specific words, which can be achieved using existing image animation methods. However, the finger motions in the generated videos are often not ideal. To address this issue, we propose the Structure-aware Temporal Consistency Network (STCNet), which jointly optimizes the prior structure of humans with temporal consistency to produce sign language videos. We use a fine-grained skeleton detector to acquire knowledge of body structure and introduce both short- and long-term cycle loss to ensure the continuity of the generated video. The two losses and keypoint detector network are optimized in an end-to-end manner. Quantitative and qualitative evaluations on three widely used datasets, namely LSA64, Phoenix-2014T, and WLASL-2000, demonstrate the effectiveness of the proposed method. It is our hope that this work can contribute to future studies on sign language production.
View PDF Chat

Camera Style Adaptation for Person Re-identification

2017-01-01
Zhun Zhong , Liang Zheng , Zhedong Zheng +2 more
Being a cross-camera retrieval task, person re-identification suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this … Being a cross-camera retrieval task, person re-identification suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this paper, we explicitly consider this challenge by introducing camera style (CamStyle) adaptation. CamStyle can serve as a data augmentation approach that smooths the camera style disparities. Specifically, with CycleGAN, labeled training images can be style-transferred to each camera, and, along with the original training samples, form the augmented training set. This method, while increasing data diversity against over-fitting, also incurs a considerable level of noise. In the effort to alleviate the impact of noise, the label smooth regularization (LSR) is adopted. The vanilla version of our method (without LSR) performs reasonably well on few-camera systems in which over-fitting often occurs. With LSR, we demonstrate consistent improvement in all systems regardless of the extent of over-fitting. We also report competitive accuracy compared with the state of the art.
View PDF Chat

Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval

2018-01-01
Zhedong Zheng , Liang Zheng , Yi Yang +1 more
Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges … Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges in applying prevailing image recognition attack methods to image retrieval. First, image retrieval demands discriminative visual features, which is significantly different from the one-hot class prediction in image recognition. Second, due to the disjoint and potentially unrelated classes between the training and test set in image retrieval, predicting the query category from predefined training classes is not accurate and leads to a sub-optimal adversarial gradient. To address these limitations, we propose a new white-box attack approach, Opposite-Direction Feature Attack (ODFA), to generate adversarial queries. Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space. To our knowledge, we are among the early attempts to design an attack method specifically for image retrieval. When we deploy an attacked image as the query, the true matches are prone to receive low ranks. We demonstrate through extensive experiments that (1) only crafting adversarial queries is sufficient to fool the state-of-the-art retrieval systems; (2) the proposed attack method, ODFA, leads to a higher attack success rate than classification attack methods, validating the necessity of leveraging characteristics of image retrieval; (3) the adversarial queries generated by our method have good transferability to other retrieval models without accessing their parameters, i.e.,the black-box setting.

Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark

2022-01-01
Jianwu Fang , Leilei Li , Kuan Yang +3 more
Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on … Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on the spatial-temporal correlation of object-level context, while they do not fit the inherent long-tailed data distribution well and are vulnerable to severe environmental change. In this work, we propose a Cognitive Accident Prediction (CAP) method that explicitly leverages human-inspired cognition of text description on the visual observation and the driver attention to facilitate model training. In particular, the text description provides a dense semantic description guidance for the primary context of the traffic scene, while the driver attention provides a traction to focus on the critical region closely correlating with safe driving. CAP is formulated by an attentive text-to-vision shift fusion module, an attentive scene context transfer module, and the driver attention guided accident prediction module. We leverage the attention mechanism in these modules to explore the core semantic cues for accident prediction. In order to train CAP, we extend an existing self-collected DADA-2000 dataset (with annotated driver attention for each frame) with further factual text descriptions for the visual observations before the accidents. Besides, we construct a new large-scale benchmark consisting of 11,727 in-the-wild accident videos with over 2.19 million frames (named as CAP-DATA) together with labeled fact-effect-reason-introspection description and temporal accident frame label. Based on extensive experiments, the superiority of CAP is validated compared with state-of-the-art approaches. The code, CAP-DATA, and all results will be released in \url{https://github.com/JWFanggit/LOTVS-CAP}.
View PDF Chat

Learnable Pillar-based Re-ranking for Image-Text Retrieval

2023-07-18
Leigang Qu , Meng Liu , Wenjie Wang +3 more
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches … Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.
View PDF Chat

Point Cloud Pre-training by Mixing and Disentangling

2021-09-01
Chao Sun , Zhedong Zheng , Xiaohan Wang +2 more
The annotation for large-scale point clouds is still time-consuming and unavailable for many real-world tasks. Point cloud pre-training is one potential solution for obtaining a scalable model for fast adaptation. … The annotation for large-scale point clouds is still time-consuming and unavailable for many real-world tasks. Point cloud pre-training is one potential solution for obtaining a scalable model for fast adaptation. Therefore, in this paper, we investigate a new self-supervised learning approach, called Mixing and Disentangling (MD), for point cloud pre-training. As the name implies, we explore how to separate the original point cloud from the mixed point cloud, and leverage this challenging task as a pretext optimization objective for model training. Considering the limited training data in the original dataset, which is much less than prevailing ImageNet, the mixing process can efficiently generate more high-quality samples. We build one baseline network to verify our intuition, which simply contains two modules, encoder and decoder. Given a mixed point cloud, the encoder is first pre-trained to extract the semantic embedding. Then an instance-adaptive decoder is harnessed to disentangle the point clouds according to the embedding. Albeit simple, the encoder is inherently able to capture the point cloud keypoints after training and can be fast adapted to downstream tasks including classification and segmentation by the pre-training and fine-tuning paradigm. Extensive experiments on two datasets show that the encoder + ours (MD) significantly surpasses that of the encoder trained from scratch and converges quickly. In ablation studies, we further study the effect of each component and discuss the advantages of the proposed self-supervised learning strategy. We hope this self-supervised learning attempt on point clouds can pave the way for reducing the deeply-learned model dependence on large-scale labeled data and saving a lot of annotation costs in the future.
View PDF Chat

Unsupervised Scene Adaptation with Memory Regularization in vivo

2019-01-01
Zhedong Zheng , Yi Yang
We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and … We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the intra-domain knowledge and inherent uncertainty learned by the network are under-explored. In this paper, we propose an orthogonal method, called memory regularization in vivo to exploit the intra-domain knowledge and regularize the model training. Specifically, we refer to the segmentation model itself as the memory module, and minor the discrepancy of the two classifiers, i.e., the primary classifier and the auxiliary classifier, to reduce the prediction inconsistency. Without extra parameters, the proposed method is complementary to the most existing domain adaptation methods and could generally improve the performance of existing methods. Albeit simple, we verify the effectiveness of memory regularization on two synthetic-to-real benchmarks: GTA5 -&gt; Cityscapes and SYNTHIA -&gt; Cityscapes, yielding +11.1% and +11.3% mIoU improvement over the baseline model, respectively. Besides, a similar +12.0% mIoU improvement is observed on the cross-city benchmark: Cityscapes -&gt; Oxford RobotCar.
View PDF Chat

Multiple-environment Self-adaptive Network for Aerial-view Geo-localization

2022-01-01
Tingyu Wang , Zhedong Zheng , Yaoqi Sun +3 more
Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key … Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key underpinning this task is to design a series of deep neural networks to learn discriminative image descriptors. However, existing methods meet large performance drops under realistic weather, such as rain and fog, since they do not take the domain shift between the training data and multiple test environments into consideration. To minor this domain gap, we propose a Multiple-environment Self-adaptive Network (MuSe-Net) to dynamically adjust the domain shift caused by environmental changing. In particular, MuSe-Net employs a two-branch neural network containing one multiple-environment style extraction network and one self-adaptive feature extraction network. As the name implies, the multiple-environment style extraction network is to extract the environment-related style information, while the self-adaptive feature extraction network utilizes an adaptive modulation module to dynamically minimize the environment-related style gap. Extensive experiments on two widely-used benchmarks, i.e., University-1652 and CVUSA, demonstrate that the proposed MuSe-Net achieves a competitive result for geo-localization in multiple environments. Furthermore, we observe that the proposed method also shows great potential to the unseen extreme weather, such as mixing the fog, rain and snow.
View PDF Chat

Relieving Triplet Ambiguity: Consensus Network for Language-Guided Image Retrieval

2023-01-01
Xu Zhang , Zhedong Zheng , Xiaohan Wang +1 more
Language-guided image retrieval enables users to search for images and interact with the retrieval system more naturally and expressively by using a reference image and a relative caption as a … Language-guided image retrieval enables users to search for images and interact with the retrieval system more naturally and expressively by using a reference image and a relative caption as a query. Most existing studies mainly focus on designing image-text composition architecture to extract discriminative visual-linguistic relations. Despite great success, we identify an inherent problem that obstructs the extraction of discriminative features and considerably compromises model training: \textbf{triplet ambiguity}. This problem stems from the annotation process wherein annotators view only one triplet at a time. As a result, they often describe simple attributes, such as color, while neglecting fine-grained details like location and style. This leads to multiple false-negative candidates matching the same modification text. We propose a novel Consensus Network (Css-Net) that self-adaptively learns from noisy triplets to minimize the negative effects of triplet ambiguity. Inspired by the psychological finding that groups perform better than individuals, Css-Net comprises 1) a consensus module featuring four distinct compositors that generate diverse fused image-text embeddings and 2) a Kullback-Leibler divergence loss, which fosters learning among the compositors, enabling them to reduce biases learned from noisy triplets and reach a consensus. The decisions from four compositors are weighted during evaluation to further achieve consensus. Comprehensive experiments on three datasets demonstrate that Css-Net can alleviate triplet ambiguity, achieving competitive performance on benchmarks, such as $+2.77\%$ R@10 and $+6.67\%$ R@50 on FashionIQ.
View PDF Chat

Unsupervised Eyeglasses Removal in the Wild

2019-01-01
Bingwen Hu , Zhedong Zheng , Ping Liu +2 more
Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses and sunglasses, and recovering appropriate eyes. Due to the large visual variants, the conventional methods … Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses and sunglasses, and recovering appropriate eyes. Due to the large visual variants, the conventional methods lack scalability. Most existing works focus on the frontal face images in the controlled environment, such as the laboratory, and need to design specific systems for different eyeglass types. To address the limitation, we propose a unified eyeglass removal model called Eyeglasses Removal Generative Adversarial Network (ERGAN), which could handle different types of glasses in the wild. The proposed method does not depend on the dense annotation of eyeglasses location but benefits from the large-scale face images with weak annotations. Specifically, we study the two relevant tasks simultaneously, i.e., removing and wearing eyeglasses. Given two facial images with and without eyeglasses, the proposed model learns to swap the eye area in two faces. The generation mechanism focuses on the eye area and invades the difficulty of generating a new face. In the experiment, we show the proposed method achieves a competitive removal quality in terms of realism and diversity. Furthermore, we evaluate ERGAN on several subsequent tasks, such as face verification and facial expression recognition. The experiment shows that our method could serve as a pre-processing method for these tasks.
View PDF Chat

Person Re-identification in the 3D Space.

2020-06-08
Zhedong Zheng , Yi Yang
People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the representation learning in a 2D space, intrinsically limiting the understanding of people. In this … People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel Omni-scale Graph Network (OG-Net) to learn the representation from sparse 3D points. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space. Extensive experiments show that the proposed method achieves competitive results on three popular large-scale person re-id datasets, and has good scalability to unseen datasets.

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

2021-01-01
Chuchu Han , Zhedong Zheng , Changxin Gao +2 more
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and … The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.
View PDF Chat

Less is More: Sparse Sampling for Dense Reaction Predictions

2021-01-01
Kezhou Lin , Xiaohan Wang , Zhedong Zheng +2 more
Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our … Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our method for 2021 Evoked Expression from Videos Challenge. In particular, our model utilizes both audio and image modalities as inputs to predict emotion changes of viewers. To model long-range emotion changes, we use a GRU-based model to predict one sparse signal with 1Hz. We observe that the emotion changes are smooth. Therefore, the final dense prediction is obtained via linear interpolating the signal, which is robust to the prediction fluctuation. Albeit simple, the proposed method has achieved pearson's correlation score of 0.04430 on the final private test set.

3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective

2022-01-01
Zhedong Zheng , Jiayin Zhu , Wei Ji +2 more
This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we … This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we observe that three primary challenges remain: (1) 3D ground-truth meshes of clothing are usually inaccessible due to annotation difficulties and time costs; (2) Conventional template-based methods are limited to modeling non-rigid objects, e.g., handbags and dresses, which are common in fashion images; (3) The inherent ambiguity compromises the model training, such as the dilemma between a large shape with a remote camera or a small shape with a close camera. In an attempt to address the above limitations, we propose a causality-aware self-supervised learning method to adaptively reconstruct 3D non-rigid objects from 2D images without 3D annotations. In particular, to solve the inherent ambiguity among four implicit variables, i.e., camera position, shape, texture, and illumination, we introduce an explainable structural causal map (SCM) to build our model. The proposed model structure follows the spirit of the causal map, which explicitly considers the prior template in the camera estimation and shape prediction. When optimization, the causality intervention tool, i.e., two expectation-maximization loops, is deeply embedded in our algorithm to (1) disentangle four encoders and (2) facilitate the prior template. Extensive experiments on two 2D fashion benchmarks (ATR and Market-HQ) show that the proposed method could yield high-fidelity 3D reconstruction. Furthermore, we also verify the scalability of the proposed method on a fine-grained bird dataset, i.e., CUB. The code is available at https://github.com/layumi/ 3D-Magic-Mirror .
View PDF Chat

A Large-scale Interpretable Multi-modality Benchmark for Facial Image Forgery Localization

2024-12-27
Jun Lian , Lingyu Liu , Yaxiong Wang +3 more
Image forgery localization, which centers on identifying tampered pixels within an image, has seen significant advancements. Traditional approaches often model this challenge as a variant of image segmentation, treating the … Image forgery localization, which centers on identifying tampered pixels within an image, has seen significant advancements. Traditional approaches often model this challenge as a variant of image segmentation, treating the binary segmentation of forged areas as the end product. We argue that the basic binary forgery mask is inadequate for explaining model predictions. It doesn't clarify why the model pinpoints certain areas and treats all forged pixels the same, making it hard to spot the most fake-looking parts. In this study, we mitigate the aforementioned limitations by generating salient region-focused interpretation for the forgery images. To support this, we craft a Multi-Modal Tramper Tracing (MMTT) dataset, comprising facial images manipulated using deepfake techniques and paired with manual, interpretable textual annotations. To harvest high-quality annotation, annotators are instructed to meticulously observe the manipulated images and articulate the typical characteristics of the forgery regions. Subsequently, we collect a dataset of 128,303 image-text pairs. Leveraging the MMTT dataset, we develop ForgeryTalker, an architecture designed for concurrent forgery localization and interpretation. ForgeryTalker first trains a forgery prompter network to identify the pivotal clues within the explanatory text. Subsequently, the region prompter is incorporated into multimodal large language model for finetuning to achieve the dual goals of localization and interpretation. Extensive experiments conducted on the MMTT dataset verify the superior performance of our proposed model. The dataset, code as well as pretrained checkpoints will be made publicly available to facilitate further research and ensure the reproducibility of our results.
View PDF Chat

Near Large Far Small: Relative Distance Based Partition Learning for UAV-view Geo-Localization

2024-12-16
Quan Chen , Tingyu Wang , Rongfeng Lu +3 more
UAV-view Geo-Localization (UVGL) presents substantial challenges, primarily due to appearance differences between drone-view and satellite-view. Existing methods develop partition learning strategies aimed at mining more comprehensive information by constructing diverse … UAV-view Geo-Localization (UVGL) presents substantial challenges, primarily due to appearance differences between drone-view and satellite-view. Existing methods develop partition learning strategies aimed at mining more comprehensive information by constructing diverse part-level feature representations, which rely on consistent cross-view scales. However, variations of UAV flight state leads to the scale mismatch of cross-views, resulting in serious performance degradation of partition-based methods. To overcome this issue, we propose a partition learning framework based on relative distance, which alleviates the dependence on scale consistency while mining fine-grained features. Specifically, we propose a distance guided dynamic partition learning strategy (DGDPL), consisting of a square partition strategy and a dynamic-guided adjustment strategy. The former is utilized to extract fine-grained features and global features in a simple manner. The latter calculates the relative distance ratio between drone- and satellite-view to adjust the partition size, thereby aligning the semantic information between partition pairs. Furthermore, we propose a saliency-guided refinement strategy to refine part-level features, so as to further improve the retrieval accuracy. Extensive experiments show that our approach achieves superior geo-localization accuracy across various scale-inconsistent scenarios, and exhibits remarkable robustness against scale variations. The code will be released.
View PDF Chat

CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution

2024-12-16
Bingwen Hu , Heng Liu , Zhedong Zheng +1 more
Convolutional Neural Networks (CNNs) have advanced Image Super-Resolution (SR), but most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly with severe downsampling (e.g., 8x … Convolutional Neural Networks (CNNs) have advanced Image Super-Resolution (SR), but most CNN-based methods rely solely on pixel-based transformations, often leading to artifacts and blurring, particularly with severe downsampling (e.g., 8x or 16x). Recent text-guided SR methods attempt to leverage textual information for enhanced detail, but they frequently struggle with effective alignment, resulting in inconsistent semantic coherence. To address these limitations, we introduce a multi-modal semantic enhancement approach that combines textual semantics with visual features, effectively tackling semantic mismatches and detail loss in highly degraded LR images. Our proposed multi-modal collaborative framework enables the production of realistic and high-quality SR images at significant up-scaling factors. The framework integrates text and image inputs, employing a prompt predictor, Text-Image Fusion Block (TIFBlock), and Iterative Refinement Module alongside CLIP (Contrastive Language-Image Pretraining) features to guide a progressive enhancement process with fine-grained alignment. This alignment produces high-resolution outputs with crisp details and semantic coherence, even at large scaling factors. Through extensive comparative experiments and ablation studies, we validate the effectiveness of our approach. Additionally, by incorporating textual semantic guidance, our technique enables a degree of super-resolution editability while maintaining semantic coherence.
View PDF Chat

Towards Rich Emotions in 3D Avatars: A Text-to-3D Avatar Generation Benchmark

2024-12-03
Haidong Xu , Meishan Zhang , Hao Ju +5 more
Producing emotionally dynamic 3D facial avatars with text derived from spoken words (Emo3D) has been a pivotal research topic in 3D avatar generation. While progress has been made in general-purpose … Producing emotionally dynamic 3D facial avatars with text derived from spoken words (Emo3D) has been a pivotal research topic in 3D avatar generation. While progress has been made in general-purpose 3D avatar generation, the exploration of generating emotional 3D avatars remains scarce, primarily due to the complexities of identifying and rendering rich emotions from spoken words. This paper reexamines Emo3D generation and draws inspiration from human processes, breaking down Emo3D into two cascading steps: Text-to-3D Expression Mapping (T3DEM) and 3D Avatar Rendering (3DAR). T3DEM is the most crucial step in determining the quality of Emo3D generation and encompasses three key challenges: Expression Diversity, Emotion-Content Consistency, and Expression Fluidity. To address these challenges, we introduce a novel benchmark to advance research in Emo3D generation. First, we present EmoAva, a large-scale, high-quality dataset for T3DEM, comprising 15,000 text-to-3D expression mappings that characterize the aforementioned three challenges in Emo3D generation. Furthermore, we develop various metrics to effectively evaluate models against these identified challenges. Next, to effectively model the consistency, diversity, and fluidity of human expressions in the T3DEM step, we propose the Continuous Text-to-Expression Generator, which employs an autoregressive Conditional Variational Autoencoder for expression code generation, enhanced with Latent Temporal Attention and Expression-wise Attention mechanisms. Finally, to further enhance the 3DAR step on rendering higher-quality subtle expressions, we present the Globally-informed Gaussian Avatar (GiGA) model. GiGA incorporates a global information mechanism into 3D Gaussian representations, enabling the capture of subtle micro-expressions and seamless transitions between emotional states.
View PDF Chat

RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning

2024-11-27
Jiacheng Wang , Zhedong Zheng , Wei Xu +1 more
Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, … Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape. Recent methods often utilize intermediate media, such as multi-view images or videos, to bridge the gap between input image and the 3D target, thereby guiding the generation of both shape and texture. However, inconsistencies in the generated multi-view snapshots frequently introduce noise and artifacts along object boundaries, undermining the 3D reconstruction process. To address this challenge, we leverage 3D Gaussian Splatting (3DGS) for 3D reconstruction, and explicitly integrate uncertainty-aware learning into the reconstruction process. By capturing the stochasticity between two Gaussian models, we estimate an uncertainty map, which is subsequently used for uncertainty-aware regularization to rectify the impact of inconsistencies. Specifically, we optimize both Gaussian models simultaneously, calculating the uncertainty map by evaluating the discrepancies between rendered images from identical viewpoints. Based on the uncertainty map, we apply adaptive pixel-wise loss weighting to regularize the models, reducing reconstruction intensity in high-uncertainty regions. This approach dynamically detects and mitigates conflicts in multi-view labels, leading to smoother results and effectively reducing artifacts. Extensive experiments show the effectiveness of our method in improving 3D generation quality by reducing inconsistencies and artifacts.
View PDF Chat

Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search

2024-11-26
Shuyu Yang , Yaxiong Wang , Zhu Li +1 more
Text-based person search aims to retrieve specific individuals across camera networks using natural language descriptions. However, current benchmarks often exhibit biases towards common actions like walking or standing, neglecting the … Text-based person search aims to retrieve specific individuals across camera networks using natural language descriptions. However, current benchmarks often exhibit biases towards common actions like walking or standing, neglecting the critical need for identifying abnormal behaviors in real-world scenarios. To meet such demands, we propose a new task, text-based person anomaly search, locating pedestrians engaged in both routine or anomalous activities via text. To enable the training and evaluation of this new task, we construct a large-scale image-text Pedestrian Anomaly Behavior (PAB) benchmark, featuring a broad spectrum of actions, e.g., running, performing, playing soccer, and the corresponding anomalies, e.g., lying, being hit, and falling of the same identity. The training set of PAB comprises 1,013,605 synthesized image-text pairs of both normalities and anomalies, while the test set includes 1,978 real-world image-text pairs. To validate the potential of PAB, we introduce a cross-modal pose-aware framework, which integrates human pose patterns with identity-based hard negative pair sampling. Extensive experiments on the proposed benchmark show that synthetic training data facilitates the fine-grained behavior retrieval in the real-world test set, while the proposed pose-aware method further improves the recall@1 by 2.88%. We will release the dataset, code, and checkpoints to facilitate further research and ensure the reproducibility of our results.
View PDF Chat

Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization

2024-11-19
Hao Ju , Zhedong Zheng
Existing approaches to drone visual geo-localization predominantly adopt the image-based setting, where a single drone-view snapshot is matched with images from other platforms. Such task formulation, however, underutilizes the inherent … Existing approaches to drone visual geo-localization predominantly adopt the image-based setting, where a single drone-view snapshot is matched with images from other platforms. Such task formulation, however, underutilizes the inherent video output of the drone and is sensitive to occlusions and environmental constraints. To address these limitations, we formulate a new video-based drone geo-localization task and propose the Video2BEV paradigm. This paradigm transforms the video into a Bird's Eye View (BEV), simplifying the subsequent matching process. In particular, we employ Gaussian Splatting to reconstruct a 3D scene and obtain the BEV projection. Different from the existing transform methods, \eg, polar transform, our BEVs preserve more fine-grained details without significant distortion. To further improve model scalability toward diverse BEVs and satellite figures, our Video2BEV paradigm also incorporates a diffusion-based module for generating hard negative samples, which facilitates discriminative feature learning. To validate our approach, we introduce UniV, a new video-based geo-localization dataset that extends the image-based University-1652 dataset. UniV features flight paths at $30^\circ$ and $45^\circ$ elevation angles with increased frame rates of up to 10 frames per second (FPS). Extensive experiments on the UniV dataset show that our Video2BEV paradigm achieves competitive recall rates and outperforms conventional video-based methods. Compared to other methods, our proposed approach exhibits robustness at lower elevations with more occlusions.
View PDF Chat

VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation

2024-11-17
Ruiyang Zhang , Hu Zhang , Zhedong Zheng
Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety … Given the higher information load processed by large vision-language models (LVLMs) compared to single-modal LLMs, detecting LVLM hallucinations requires more human and time expense, and thus rise a wider safety concerns. In this paper, we introduce VL-Uncertainty, the first uncertainty-based framework for detecting hallucinations in LVLMs. Different from most existing methods that require ground-truth or pseudo annotations, VL-Uncertainty utilizes uncertainty as an intrinsic metric. We measure uncertainty by analyzing the prediction variance across semantically equivalent but perturbed prompts, including visual and textual data. When LVLMs are highly confident, they provide consistent responses to semantically equivalent queries. However, when uncertain, the responses of the target LVLM become more random. Considering semantically similar answers with different wordings, we cluster LVLM responses based on their semantic content and then calculate the cluster distribution entropy as the uncertainty measure to detect hallucination. Our extensive experiments on 10 LVLMs across four benchmarks, covering both free-form and multi-choice tasks, show that VL-Uncertainty significantly outperforms strong baseline methods in hallucination detection.
View PDF Chat

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

2024-10-14
Guiyu Zhang , Huan-ang Gao , Zijian Jiang +2 more
In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both … In this paper, we focus on the task of conditional image generation, where an image is synthesized according to user instructions. The critical challenge underpinning this task is ensuring both the fidelity of the generated images and their semantic alignment with the provided conditions. To tackle this issue, previous studies have employed supervised perceptual losses derived from pre-trained models, i.e., reward models, to enforce alignment between the condition and the generated result. However, we observe one inherent shortcoming: considering the diversity of synthesized images, the reward model usually provides inaccurate feedback when encountering newly generated data, which can undermine the training process. To address this limitation, we propose an uncertainty-aware reward modeling, called Ctrl-U, including uncertainty estimation and uncertainty-aware regularization, designed to reduce the adverse effects of imprecise feedback from the reward model. Given the inherent cognitive uncertainty within reward models, even images generated under identical conditions often result in a relatively large discrepancy in reward loss. Inspired by the observation, we explicitly leverage such prediction variance as an uncertainty indicator. Based on the uncertainty estimation, we regularize the model training by adaptively rectifying the reward. In particular, rewards with lower uncertainty receive higher loss weights, while those with higher uncertainty are given reduced weights to allow for larger variability. The proposed uncertainty regularization facilitates reward fine-tuning through consistency construction. Extensive experiments validate the effectiveness of our methodology in improving the controllability and generation quality, as well as its scalability across diverse conditional scenarios. Code will soon be available at https://grenoble-zhang.github.io/Ctrl-U-Page/.
View PDF Chat

Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection

2024-08-01
Ruiyang Zhang , Hu Zhang , Hang Yu +1 more
Unsupervised 3D object detection aims to identify objects of interest from unlabeled raw data, such as LiDAR points. Recent approaches usually adopt pseudo 3D bounding boxes (3D bboxes) from clustering … Unsupervised 3D object detection aims to identify objects of interest from unlabeled raw data, such as LiDAR points. Recent approaches usually adopt pseudo 3D bounding boxes (3D bboxes) from clustering algorithm to initialize the model training, and then iteratively updating both pseudo labels and the trained model. However, pseudo bboxes inevitably contain noises, and such inaccurate annotation accumulates to the final model, compromising the performance. Therefore, in an attempt to mitigate the negative impact of pseudo bboxes, we introduce a new uncertainty-aware framework. In particular, Our method consists of two primary components: uncertainty estimation and uncertainty regularization. (1) In the uncertainty estimation phase, we incorporate an extra auxiliary detection branch alongside the primary detector. The prediction disparity between the primary and auxiliary detectors is leveraged to estimate uncertainty at the box coordinate level, including position, shape, orientation. (2) Based on the assessed uncertainty, we regularize the model training via adaptively adjusting every 3D bboxes coordinates. For pseudo bbox coordinates with high uncertainty, we assign a relatively low loss weight. Experiment verifies that the proposed method is robust against the noisy pseudo bboxes, yielding substantial improvements on nuScenes and Lyft compared to existing techniques, with increases of 6.9% in AP$_{BEV}$ and 2.5% in AP$_{3D}$ on nuScenes, and 2.2% in AP$_{BEV}$ and 1.0% in AP$_{3D}$ on Lyft.
View PDF Chat

Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene

2024-07-11
Ruiyang Zhang , Hu Zhang , Hang Yu +1 more
The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance … The unsupervised 3D object detection is to accurately detect objects in unstructured environments with no explicit supervisory signals. This task, given sparse LiDAR point clouds, often results in compromised performance for detecting distant or small objects due to the inherent sparsity and limited spatial resolution. In this paper, we are among the early attempts to integrate LiDAR data with 2D images for unsupervised 3D detection and introduce a new method, dubbed LiDAR-2D Self-paced Learning (LiSe). We argue that RGB images serve as a valuable complement to LiDAR data, offering precise 2D localization cues, particularly when scarce LiDAR points are available for certain objects. Considering the unique characteristics of both modalities, our framework devises a self-paced learning pipeline that incorporates adaptive sampling and weak model aggregation strategies. The adaptive sampling strategy dynamically tunes the distribution of pseudo labels during training, countering the tendency of models to overfit easily detected samples, such as nearby and large-sized objects. By doing so, it ensures a balanced learning trajectory across varying object scales and distances. The weak model aggregation component consolidates the strengths of models trained under different pseudo label distributions, culminating in a robust and powerful final model. Experimental evaluations validate the efficacy of our proposed LiSe method, manifesting significant improvements of +7.1% AP$_{BEV}$ and +3.4% AP$_{3D}$ on nuScenes, and +8.3% AP$_{BEV}$ and +7.4% AP$_{3D}$ on Lyft compared to existing techniques.
View PDF Chat

From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person Search

2024-04-16
Jintao Sun , Zhedong Zheng , Gangyi Ding
In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized … In text-based person search endeavors, data generation has emerged as a prevailing practice, addressing concerns over privacy preservation and the arduous task of manual annotation. Although the number of synthesized data can be infinite in theory, the scientific conundrum persists that how much generated data optimally fuels subsequent model training. We observe that only a subset of the data in these constructed datasets plays a decisive role. Therefore, we introduce a new Filtering-WoRA paradigm, which contains a filtering algorithm to identify this crucial data subset and WoRA (Weighted Low-Rank Adaptation) learning strategy for light fine-tuning. The filtering algorithm is based on the cross-modality relevance to remove the lots of coarse matching synthesis pairs. As the number of data decreases, we do not need to fine-tune the entire model. Therefore, we propose a WoRA learning strategy to efficiently update a minimal portion of model parameters. WoRA streamlines the learning process, enabling heightened efficiency in extracting knowledge from fewer, yet potent, data instances. Extensive experimentation validates the efficacy of pretraining, where our model achieves advanced and efficient retrieval performance on challenging real-world benchmarks. Notably, on the CUHK-PEDES dataset, we have achieved a competitive mAP of 67.02% while reducing model training time by 19.82%.
View PDF Chat

Multiple-environment Self-adaptive Network for aerial-view geo-localization

2024-03-12
Tingyu Wang , Zhedong Zheng , Yaoqi Sun +3 more
View PDF Chat

Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation

2024-02-16
Yucheng Suo , Zhedong Zheng , Xiaohan Wang +2 more
Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate … Sign language provides a way for differently-abled individuals to express their feelings and emotions. However, learning sign language can be challenging and time consuming. An alternative approach is to animate user photos using sign language videos of specific words, which can be achieved using existing image animation methods. However, the finger motions in the generated videos are often not ideal. To address this issue, we propose the Structure-aware Temporal Consistency Network (STCNet), which jointly optimizes the prior structure of humans with temporal consistency to produce sign language videos. We use a fine-grained skeleton detector to acquire knowledge of body structure and introduce both short- and long-term cycle loss to ensure the continuity of the generated video. The two losses and keypoint detector network are optimized in an end-to-end manner. Quantitative and qualitative evaluations on three widely used datasets, namely LSA64, Phoenix-2014T, and WLASL-2000, demonstrate the effectiveness of the proposed method. It is our hope that this work can contribute to future studies on sign language production.
View PDF Chat

Instilling Multi-round Thinking to Text-guided Image Generation

2024-01-01
Lidong Zeng , Zhedong Zheng , Yinwei Wei +1 more
This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge … This paper delves into the text-guided image editing task, focusing on modifying a reference image according to user-specified textual feedback to embody specific attributes. Despite recent advancements, a persistent challenge remains that the single-round generation often overlooks crucial details, particularly in the realm of fine-grained changes like shoes or sleeves. This issue compounds over multiple rounds of interaction, severely limiting customization quality. In an attempt to address this challenge, we introduce a new self-supervised regularization, \ie, multi-round regularization, which is compatible with existing methods. Specifically, the multi-round regularization encourages the model to maintain consistency across different modification orders. It builds upon the observation that the modification order generally should not affect the final result. Different from traditional one-round generation, the mechanism underpinning the proposed method is the error amplification of initially minor inaccuracies in capturing intricate details. Qualitative and quantitative experiments affirm that the proposed method achieves high-fidelity editing quality, especially the local modification, in both single-round and multiple-round generation, while also showcasing robust generalization to irregular text inputs. The effectiveness of our semantic alignment with textual feedback is further substantiated by the retrieval improvements on FahisonIQ and Fashion200k.

Collaborative Group: Composed Image Retrieval Via Consensus Learning from Noisy Annotations

2024-01-01
Xu Zhang , Zhedong Zheng , Linchao Zhu +1 more
Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI
View PDF Chat

Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark

2023-10-26
Shuyu Yang , Yinan Zhou , Zhedong Zheng +3 more
In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and … In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 × larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96 %, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively. The dataset, model, and code are available at https://github.com/Shuyu-XJTU/APTM.
View PDF Chat

PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation

2023-10-26
Mu Chen , Zhedong Zheng , Yi Yang +1 more
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., … Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an image, remains under-explored. In an attempt to fill this gap, we revisit the current pixel contrast in semantic segmentation and propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts. The proposed framework exploits the inherent structures of intra-domain images, which: (1) explicitly encourages learning the discriminative pixel-wise features with intra-class compactness and inter-class separability, and (2) motivates the robust feature learning of the identical patch against different contexts or fluctuations. Extensive experiments verify the effectiveness of the proposed method, which obtains competitive accuracy on the two widely-used UDA benchmarks, e.g., 75.6 mIoU on GTA→Cityscapes and 68.2 mIoU on Synthia→Cityscapes. Moreover, our method is compatible with other UDA approaches to further improve the performance without introducing extra parameters.
View PDF Chat

Learnable Pillar-based Re-ranking for Image-Text Retrieval

2023-07-18
Leigang Qu , Meng Liu , Wenjie Wang +3 more
Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches … Image-text retrieval aims to bridge the modality gap and retrieve cross-modal content based on semantic similarities. Prior work usually focuses on the pairwise relations (i.e., whether a data sample matches another) but ignores the higher-order neighbor relations (i.e., a matching structure among multiple data samples). Re-ranking, a popular post-processing practice, has revealed the superiority of capturing neighbor relations in single-modality retrieval tasks. However, it is ineffective to directly extend existing re-ranking algorithms to image-text retrieval. In this paper, we analyze the reason from four perspectives, i.e., generalization, flexibility, sparsity, and asymmetry, and propose a novel learnable pillar-based re-ranking paradigm. Concretely, we first select top-ranked intra- and inter-modal neighbors as pillars, and then reconstruct data samples with the neighbor relations between them and the pillars. In this way, each sample can be mapped into a multimodal pillar space only using similarities, ensuring generalization. After that, we design a neighbor-aware graph reasoning module to flexibly exploit the relations and excavate the sparse positive items within a neighborhood. We also present a structure alignment constraint to promote cross-modal collaboration and align the asymmetric modalities. On top of various base backbones, we carry out extensive experiments on two benchmark datasets, i.e., Flickr30K and MS-COCO, demonstrating the effectiveness, superiority, generalization, and transferability of our proposed re-ranking paradigm.
View PDF Chat

Progressive Local Filter Pruning for Image Retrieval Acceleration

2023-01-01
Xiaodong Wang , Zhedong Zheng , Yang He +3 more
This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the … This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the model inference, which should be taken into consideration in real-world practice. The challenge of pruning image retrieval models is that the middle-level feature should be preserved as much as possible. Such different requirements of the retrieval and classification model make the traditional pruning methods not that suitable for our task. To solve the problem, we propose a new Progressive Local Filter Pruning (PLFP) method for image retrieval acceleration. Specifically, layer by layer, we analyze the local geometric properties of each filter and select the one that can be replaced by the neighbors. Then we progressively prune the filter by gradually changing the filter weights. In this way, the representation ability of the model is preserved. To verify this, we evaluate our method on two widely-used image retrieval datasets,i.e., Oxford5k and Paris6K, and one person re-identification dataset,i.e., Market-1501. The proposed method arrives with superior performance to the conventional pruning methods, suggesting the effectiveness of the proposed method for image retrieval.
View PDF Chat

Actively Discovering New Slots for Task-oriented Conversation

2023-01-01
Yuxia Wu , Tianhao Dai , Zhedong Zheng +1 more
Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging … Existing task-oriented conversational search systems heavily rely on domain ontologies with pre-defined slots and candidate value sets. In practical applications, these prerequisites are hard to meet, due to the emerging new user requirements and ever-changing scenarios. To mitigate these issues for better interaction performance, there are efforts working towards detecting out-of-vocabulary values or discovering new slots under unsupervised or semi-supervised learning paradigm. However, overemphasizing on the conversation data patterns alone induces these methods to yield noisy and arbitrary slot results. To facilitate the pragmatic utility, real-world systems tend to provide a stringent amount of human labelling quota, which offers an authoritative way to obtain accurate and meaningful slot assignments. Nonetheless, it also brings forward the high requirement of utilizing such quota efficiently. Hence, we formulate a general new slot discovery task in an information extraction fashion and incorporate it into an active learning framework to realize human-in-the-loop learning. Specifically, we leverage existing language tools to extract value candidates where the corresponding labels are further leveraged as weak supervision signals. Based on these, we propose a bi-criteria selection scheme which incorporates two major strategies, namely, uncertainty-based sampling and diversity-based sampling to efficiently identify terms of interest. We conduct extensive experiments on several public datasets and compare with a bunch of competitive baselines to demonstrate the effectiveness of our method. We have made the code and data used in this paper publicly available.
View PDF Chat

Relieving Triplet Ambiguity: Consensus Network for Language-Guided Image Retrieval

2023-01-01
Xu Zhang , Zhedong Zheng , Xiaohan Wang +1 more
Language-guided image retrieval enables users to search for images and interact with the retrieval system more naturally and expressively by using a reference image and a relative caption as a … Language-guided image retrieval enables users to search for images and interact with the retrieval system more naturally and expressively by using a reference image and a relative caption as a query. Most existing studies mainly focus on designing image-text composition architecture to extract discriminative visual-linguistic relations. Despite great success, we identify an inherent problem that obstructs the extraction of discriminative features and considerably compromises model training: \textbf{triplet ambiguity}. This problem stems from the annotation process wherein annotators view only one triplet at a time. As a result, they often describe simple attributes, such as color, while neglecting fine-grained details like location and style. This leads to multiple false-negative candidates matching the same modification text. We propose a novel Consensus Network (Css-Net) that self-adaptively learns from noisy triplets to minimize the negative effects of triplet ambiguity. Inspired by the psychological finding that groups perform better than individuals, Css-Net comprises 1) a consensus module featuring four distinct compositors that generate diverse fused image-text embeddings and 2) a Kullback-Leibler divergence loss, which fosters learning among the compositors, enabling them to reduce biases learned from noisy triplets and reach a consensus. The decisions from four compositors are weighted during evaluation to further achieve consensus. Comprehensive experiments on three datasets demonstrate that Css-Net can alleviate triplet ambiguity, achieving competitive performance on benchmarks, such as $+2.77\%$ R@10 and $+6.67\%$ R@50 on FashionIQ.
View PDF Chat

Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark

2023-01-01
Shuyu Yang , Yinan Zhou , Yaxiong Wang +3 more
In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and … In this paper, we introduce a large Multi-Attribute and Language Search dataset for text-based person retrieval, called MALS, and explore the feasibility of performing pre-training on both attribute recognition and image-text matching tasks in one stone. In particular, MALS contains 1,510,330 image-text pairs, which is about 37.5 times larger than prevailing CUHK-PEDES, and all images are annotated with 27 attributes. Considering the privacy concerns and annotation costs, we leverage the off-the-shelf diffusion models to generate the dataset. To verify the feasibility of learning from the generated data, we develop a new joint Attribute Prompt Learning and Text Matching Learning (APTM) framework, considering the shared knowledge between attribute and text. As the name implies, APTM contains an attribute prompt learning stream and a text matching learning stream. (1) The attribute prompt learning leverages the attribute prompts for image-attribute alignment, which enhances the text matching learning. (2) The text matching learning facilitates the representation learning on fine-grained details, and in turn, boosts the attribute prompt learning. Extensive experiments validate the effectiveness of the pre-training on MALS, achieving state-of-the-art retrieval performance via APTM on three challenging real-world benchmarks. In particular, APTM achieves a consistent improvement of +6.96%, +7.68%, and +16.95% Recall@1 accuracy on CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets by a clear margin, respectively.

Progressive Text-to-3D Generation for Automatic 3D Prototyping

2023-01-01
Yi Han , Zhedong Zheng , Xiangyu Xu +1 more
Text-to-3D generation is to craft a 3D object according to a natural language description. This can significantly reduce the workload for manually designing 3D models and provide a more natural … Text-to-3D generation is to craft a 3D object according to a natural language description. This can significantly reduce the workload for manually designing 3D models and provide a more natural way of interaction for users. However, this problem remains challenging in recovering the fine-grained details effectively and optimizing a large-size 3D output efficiently. Inspired by the success of progressive learning, we propose a Multi-Scale Triplane Network (MTN) and a new progressive learning strategy. As the name implies, the Multi-Scale Triplane Network consists of four triplanes transitioning from low to high resolution. The low-resolution triplane could serve as an initial shape for the high-resolution ones, easing the optimization difficulty. To further enable the fine-grained details, we also introduce the progressive learning strategy, which explicitly demands the network to shift its focus of attention from simple coarse-grained patterns to difficult fine-grained patterns. Our experiment verifies that the proposed method performs favorably against existing methods. For even the most challenging descriptions, where most existing methods struggle to produce a viable shape, our proposed method consistently delivers. We aspire for our work to pave the way for automatic 3D prototyping via natural language descriptions.
View PDF Chat

Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatially Relation Matching

2023-01-01
Meng Chu , Zhedong Zheng , Wei Ji +1 more
Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this … Navigating drones through natural language commands remains challenging due to the dearth of accessible multi-modal datasets and the stringent precision requirements for aligning visual and textual data. To address this pressing need, we introduce GeoText-1652, a new natural language-guided geo-localization benchmark. This dataset is systematically constructed through an interactive human-computer process leveraging Large Language Model (LLM) driven annotation techniques in conjunction with pre-trained vision models. GeoText-1652 extends the established University-1652 image dataset with spatial-aware text annotations, thereby establishing one-to-one correspondences between image, text, and bounding box elements. We further introduce a new optimization objective to leverage fine-grained spatial associations, called blending spatial matching, for region-level spatial relation matching. Extensive experiments reveal that our approach maintains a competitive recall rate comparing other prevailing cross-modality methods. This underscores the promising potential of our approach in elevating drone control and navigation through the seamless integration of natural language commands in real-world scenarios.
View PDF Chat

Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation

2023-01-01
Mu Chen , Zhedong Zheng , Yi Yang
Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations … Scene segmentation via unsupervised domain adaptation (UDA) enables the transfer of knowledge acquired from source synthetic data to real-world target data, which largely reduces the need for manual pixel-level annotations in the target domain. To facilitate domain-invariant feature learning, existing methods typically mix data from both the source domain and target domain by simply copying and pasting the pixels. Such vanilla methods are usually sub-optimal since they do not take into account how well the mixed layouts correspond to real-world scenarios. Real-world scenarios are with an inherent layout. We observe that semantic categories, such as sidewalks, buildings, and sky, display relatively consistent depth distributions, and could be clearly distinguished in a depth map. Based on such observation, we propose a depth-aware framework to explicitly leverage depth estimation to mix the categories and facilitate the two complementary tasks, i.e., segmentation and depth learning in an end-to-end manner. In particular, the framework contains a Depth-guided Contextual Filter (DCF) forndata augmentation and a cross-task encoder for contextual learning. DCF simulates the real-world layouts, while the cross-task encoder further adaptively fuses the complementing features between two tasks. Besides, it is worth noting that several public datasets do not provide depth annotation. Therefore, we leverage the off-the-shelf depth estimation network to generate the pseudo depth. Extensive experiments show that our proposed methods, even with pseudo depth, achieve competitive performance on two widely-used bench-marks, i.e. 77.7 mIoU on GTA to Cityscapes and 69.3 mIoU on Synthia to Cityscapes.
View PDF Chat

Parameter-Efficient Person Re-Identification in the 3D Space

2022-11-04
Zhedong Zheng , Xiaohan Wang , Nenggan Zheng +1 more
People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In … People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient Omni-scale Graph Network (OG-Net) to learn the pedestrian representation directly from 3D point clouds. OG-Net effectively exploits the local information provided by sparse 3D points and takes advantage of the structure and appearance information in a coherent manner. With the help of 3D geometry information, we can learn a new type of deep re-id feature free from noisy variants, such as scale and viewpoint. To our knowledge, we are among the first attempts to conduct person re-identification in the 3D space. We demonstrate through extensive experiments that the proposed method (1) eases the matching difficulty in the traditional 2D space, (2) exploits the complementary information of 2D appearance and 3D structure, (3) achieves competitive results with limited parameters on four large-scale person re-id datasets, and (4) has good scalability to unseen datasets. Our code, models and generated 3D human data are publicly available at https://github.com/layumi/person-reid-3d .
View PDF Chat

Self-Supervised Point Cloud Representation Learning via Separating Mixed Shapes

2022-09-14
Chao Sun , Zhedong Zheng , Xiaohan Wang +2 more
The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning … The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks, we argue that pre-training is one potential solution for obtaining a scalable model to 3D point cloud downstream tasks as well. In this paper, we, therefore, explore a new self-supervised learning method, called Mixing and Disentangling ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MD</b> ), for 3D point cloud representation learning. As the name implies, we mix two input shapes and demand the model learning to separate the inputs from the mixed shape. We leverage this reconstruction task as the pretext optimization objective for self-supervised learning. There are two primary advantages: 1) Compared to prevailing image datasets, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , ImageNet, point cloud datasets are <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">de facto</i> small. The mixing process can provide a much larger online training sample pool. 2) On the other hand, the disentangling process motivates the model to mine the geometric prior knowledge, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.</i> , key points. To verify the effectiveness of the proposed pretext task, we build one baseline network, which is composed of one encoder and one decoder. During pre-training, we mix two original shapes and obtain the geometry-aware embedding from the encoder, then an instance-adaptive decoder is applied to recover the original shapes from the embedding. Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks. The proposed method has improved the empirical performance on both ModelNet-40 and ShapeNet-Part datasets in terms of point cloud classification and segmentation tasks. We further conduct ablation studies to explore the effect of each component and verify the generalization of our proposed strategy by harnessing different backbones.
View PDF Chat

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis

2022-06-01
Xuanmeng Zhang , Zhedong Zheng , Daiheng Gao +3 more
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail … 3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.
View PDF Chat

Adaptive Boosting for Domain Adaptation: Toward Robust Predictions in Scene Segmentation

2022-01-01
Zhedong Zheng , Yi Yang
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, <i>i.e</i>., target domain. One common practice is to train the model on both … Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, <i>i.e</i>., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines deep model learning with the conventional training strategy, <i>i.e</i>., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate &#x201C;weak&#x201D; models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks.
View PDF Chat

Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis

2022-01-01
Xuanmeng Zhang , Zhedong Zheng , Daiheng Gao +3 more
3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail … 3D-aware image synthesis aims to generate images of objects from multiple views by learning a 3D representation. However, one key challenge remains: existing approaches lack geometry constraints, hence usually fail to generate multi-view consistent images. To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints. By leveraging the underlying 3D geometry information of generated images, i.e., depth and camera transformation matrix, we explicitly establish stereo correspondence between views to perform multi-view joint optimization. In particular, we enforce the photometric consistency between pairs of views and integrate a stereo mixup mechanism into the training process, encouraging the model to reason about the correct 3D shape. Besides, we design a two-stage training strategy with feature-level multi-view joint optimization to improve the image quality. Extensive experiments on three datasets demonstrate that MVCGAN achieves the state-of-the-art performance for 3D-aware image synthesis.
View PDF Chat

Multiple-environment Self-adaptive Network for Aerial-view Geo-localization

2022-01-01
Tingyu Wang , Zhedong Zheng , Yaoqi Sun +3 more
Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key … Aerial-view geo-localization tends to determine an unknown position through matching the drone-view image with the geo-tagged satellite-view image. This task is mostly regarded as an image retrieval problem. The key underpinning this task is to design a series of deep neural networks to learn discriminative image descriptors. However, existing methods meet large performance drops under realistic weather, such as rain and fog, since they do not take the domain shift between the training data and multiple test environments into consideration. To minor this domain gap, we propose a Multiple-environment Self-adaptive Network (MuSe-Net) to dynamically adjust the domain shift caused by environmental changing. In particular, MuSe-Net employs a two-branch neural network containing one multiple-environment style extraction network and one self-adaptive feature extraction network. As the name implies, the multiple-environment style extraction network is to extract the environment-related style information, while the self-adaptive feature extraction network utilizes an adaptive modulation module to dynamically minimize the environment-related style gap. Extensive experiments on two widely-used benchmarks, i.e., University-1652 and CVUSA, demonstrate that the proposed MuSe-Net achieves a competitive result for geo-localization in multiple environments. Furthermore, we observe that the proposed method also shows great potential to the unseen extreme weather, such as mixing the fog, rain and snow.
View PDF Chat

3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective

2022-01-01
Zhedong Zheng , Jiayin Zhu , Wei Ji +2 more
This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we … This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we observe that three primary challenges remain: (1) 3D ground-truth meshes of clothing are usually inaccessible due to annotation difficulties and time costs; (2) Conventional template-based methods are limited to modeling non-rigid objects, e.g., handbags and dresses, which are common in fashion images; (3) The inherent ambiguity compromises the model training, such as the dilemma between a large shape with a remote camera or a small shape with a close camera. In an attempt to address the above limitations, we propose a causality-aware self-supervised learning method to adaptively reconstruct 3D non-rigid objects from 2D images without 3D annotations. In particular, to solve the inherent ambiguity among four implicit variables, i.e., camera position, shape, texture, and illumination, we introduce an explainable structural causal map (SCM) to build our model. The proposed model structure follows the spirit of the causal map, which explicitly considers the prior template in the camera estimation and shape prediction. When optimization, the causality intervention tool, i.e., two expectation-maximization loops, is deeply embedded in our algorithm to (1) disentangle four encoders and (2) facilitate the prior template. Extensive experiments on two 2D fashion benchmarks (ATR and Market-HQ) show that the proposed method could yield high-fidelity 3D reconstruction. Furthermore, we also verify the scalability of the proposed method on a fine-grained bird dataset, i.e., CUB. The code is available at https://github.com/layumi/ 3D-Magic-Mirror .
View PDF Chat

SPG-VTON: Semantic Prediction Guidance for Multi-Pose Virtual Try-on

2022-01-01
Bingwen Hu , Ping Liu , Zhedong Zheng +1 more
Image-based virtual try-on is challenging in fitting a target in-shop clothes onto a reference person under diverse human poses. Previous works focus on preserving clothing details ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> … Image-based virtual try-on is challenging in fitting a target in-shop clothes onto a reference person under diverse human poses. Previous works focus on preserving clothing details ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g.,</i> texture, logos, patterns) when transferring desired clothes onto a target person under a fixed pose. However, the performances of existing methods significantly dropped when extending existing methods to multi-pose virtual try-on. In this paper, we propose an end-to-end Semantic Prediction Guidance multi-pose Virtual Try-On Network (SPG-VTON), which can fit the desired clothing into a reference person under arbitrary poses. Specifically, SPG-VTON is composed of three sub-modules. First, a Semantic Prediction Module (SPM) generates the desired semantic map. The predicted semantic map provides more abundant guidance to locate the desired clothing region and produce a coarse try-on image. Second, a Clothes Warping Module (CWM) warps in-shop clothes to the desired shape according to the predicted semantic map and the desired pose. Specifically, we introduce a conductible cycle consistency loss to alleviate the misalignment in the clothing warping process. Third, a Try-on Synthesis Module (TSM) combines the coarse result and the warped clothes to generate the final virtual try-on image, preserving details of the desired clothes and under the desired pose. In addition, we introduce a face identity loss to refine the facial appearance and maintain the identity of the final virtual try-on result at the same time. We evaluate the proposed method on the most massive multi-pose dataset (MPV) and the DeepFashion dataset. The qualitative and quantitative experiments show that SPG-VTON is superior to the state-of-the-art methods and is robust to data noise, including background and accessory changes, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> , hats and handbags, showing good scalability to the real-world scenario.
View PDF Chat

Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation

2022-01-01
Yucheng Suo , Zhedong Zheng , Xiaohan Wang +2 more
Sign language is the window for people differently-abled to express their feelings as well as emotions. However, it remains challenging for people to learn sign language in a short time. … Sign language is the window for people differently-abled to express their feelings as well as emotions. However, it remains challenging for people to learn sign language in a short time. To address this real-world challenge, in this work, we study the motion transfer system, which can transfer the user photo to the sign language video of specific words. In particular, the appearance content of the output video comes from the provided user image, while the motion of the video is extracted from the specified tutorial video. We observe two primary limitations in adopting the state-of-the-art motion transfer methods to sign language generation:(1) Existing motion transfer works ignore the prior geometrical knowledge of the human body. (2) The previous image animation methods only take image pairs as input in the training stage, which could not fully exploit the temporal information within videos. In an attempt to address the above-mentioned limitations, we propose Structure-aware Temporal Consistency Network (STCNet) to jointly optimize the prior structure of human with the temporal consistency for sign language video generation. There are two main contributions in this paper. (1) We harness a fine-grained skeleton detector to provide prior knowledge of the body keypoints. In this way, we ensure the keypoint movement in a valid range and make the model become more explainable and robust. (2) We introduce two cycle-consistency losses, i.e., short-term cycle loss and long-term cycle loss, which are conducted to assure the continuity of the generated video. We optimize the two losses and keypoint detector network in an end-to-end manner.
View PDF Chat

Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion

2022-01-01
Jian Ma , Zhedong Zheng , Hao Fei +3 more
Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice … Voice conversion is to generate a new speech with the source content and a target voice style. In this paper, we focus on one general setting, i.e., non-parallel many-to-many voice conversion, which is close to the real-world scenario. As the name implies, non-parallel many-to-many voice conversion does not require the paired source and reference speeches and can be applied to arbitrary voice transfer. In recent years, Generative Adversarial Networks (GANs) and other techniques such as Conditional Variational Autoencoders (CVAEs) have made considerable progress in this field. However, due to the sophistication of voice conversion, the style similarity of the converted speech is still unsatisfactory. Inspired by the inherent structure of mel-spectrogram, we propose a new voice conversion framework, i.e., Subband-based Generative Adversarial Network for Voice Conversion (SGAN-VC). SGAN-VC converts each subband content of the source speech separately by explicitly utilizing the spatial characteristics between different subbands. SGAN-VC contains one style encoder, one content encoder, and one decoder. In particular, the style encoder network is designed to learn style codes for different subbands of the target speaker. The content encoder network can capture the content information on the source speech. Finally, the decoder generates particular subband content. In addition, we propose a pitch-shift module to fine-tune the pitch of the source speaker, making the converted tone more accurate and explainable. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art performance on VCTK Corpus and AISHELL3 datasets both qualitatively and quantitatively, whether on seen or unseen data. Furthermore, the content intelligibility of SGAN-VC on unseen data even exceeds that of StarGANv2-VC with ASR network assistance.
View PDF Chat

Behavioral Intention Prediction in Driving Scenes: A Survey

2022-01-01
Jianwu Fang , Fan Wang , Peining Shen +3 more
In the driving scene, the road agents usually conduct frequent interactions and intention understanding of the surroundings. Ego-agent (each road agent itself) predicts what behavior will be engaged by other … In the driving scene, the road agents usually conduct frequent interactions and intention understanding of the surroundings. Ego-agent (each road agent itself) predicts what behavior will be engaged by other road users all the time and expects a shared and consistent understanding for safe movement. Behavioral Intention Prediction (BIP) simulates such a human consideration process and fulfills the early prediction of specific behaviors. Similar to other prediction tasks, such as trajectory prediction, data-driven deep learning methods have taken the primary pipeline in research. The rapid development of BIP inevitably leads to new issues and challenges. To catalyze future research, this work provides a comprehensive review of BIP from the available datasets, key factors and challenges, pedestrian-centric and vehicle-centric BIP approaches, and BIP-aware applications. Based on the investigation, data-driven deep learning approaches have become the primary pipelines. The behavioral intention types are still monotonous in most current datasets and methods (e.g., Crossing (C) and Not Crossing (NC) for pedestrians and Lane Changing (LC) for vehicles) in this field. In addition, for the safe-critical scenarios (e.g., near-crashing situations), current research is limited. Through this investigation, we identify open issues in behavioral intention prediction and suggest possible insights for future research.
View PDF Chat

Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization

2022-01-01
Tingyu Wang , Zhedong Zheng , Zunjie Zhu +3 more
Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance … Cross-view geo-localization aims to spot images of the same location shot from two platforms, e.g., the drone platform and the satellite platform. Existing methods usually focus on optimizing the distance between one embedding with others in the feature space, while neglecting the redundancy of the embedding itself. In this paper, we argue that the low redundancy is also of importance, which motivates the model to mine more diverse patterns. To verify this point, we introduce a simple yet effective regularization, i.e., Dynamic Weighted Decorrelation Regularization (DWDR), to explicitly encourage networks to learn independent embedding channels. As the name implies, DWDR regresses the embedding correlation coefficient matrix to a sparse matrix, i.e., the identity matrix, with dynamic weights. The dynamic weights are applied to focus on still correlated channels during training. Besides, we propose a cross-view symmetric sampling strategy, which keeps the example balance between different platforms. Albeit simple, the proposed method has achieved competitive results on three large-scale benchmarks, i.e., University-1652, CVUSA and CVACT. Moreover, under the harsh circumstance, e.g., the extremely short feature of 64 dimensions, the proposed method surpasses the baseline model by a clear margin.

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

2022-01-01
Yiyang Chen , Zhedong Zheng , Wei Ji +2 more
We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the … We investigate composed image retrieval with text feedback. Users gradually look for the target of interest by moving from coarse to fine-grained feedback. However, existing methods merely focus on the latter, i.e., fine-grained search, by harnessing positive and negative pairs during training. This pair-based paradigm only considers the one-to-one distance between a pair of specific points, which is not aligned with the one-to-many coarse-grained retrieval process and compromises the recall rate. In an attempt to fill this gap, we introduce a unified learning approach to simultaneously modeling the coarse- and fine-grained retrieval by considering the multi-grained uncertainty. The key idea underpinning the proposed method is to integrate fine- and coarse-grained retrieval as matching data points with small and large fluctuations, respectively. Specifically, our method contains two modules: uncertainty modeling and uncertainty regularization. (1) The uncertainty modeling simulates the multi-grained queries by introducing identically distributed fluctuations in the feature space. (2) Based on the uncertainty modeling, we further introduce uncertainty regularization to adapt the matching objective according to the fluctuation range. Compared with existing methods, the proposed strategy explicitly prevents the model from pushing away potential candidates in the early stage, and thus improves the recall rate. On the three public datasets, i.e., FashionIQ, Fashion200k, and Shoes, the proposed method has achieved +4.03%, +3.38%, and +2.40% Recall@50 accuracy over a strong baseline, respectively.
View PDF Chat

PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation

2022-01-01
Mu Chen , Zhedong Zheng , Yi Yang +1 more
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., … Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned model to other domains. The domain-invariant knowledge is transferred from the model trained on labeled source domain, e.g., video game, to unlabeled target domains, e.g., real-world scenarios, saving annotation expenses. Existing UDA methods for semantic segmentation usually focus on minimizing the inter-domain discrepancy of various levels, e.g., pixels, features, and predictions, for extracting domain-invariant knowledge. However, the primary intra-domain knowledge, such as context correlation inside an image, remains underexplored. In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts. The proposed framework exploits the inherent structures of intra-domain images, which: (1) explicitly encourages learning the discriminative pixel-wise features with intra-class compactness and inter-class separability, and (2) motivates the robust feature learning of the identical patch against different contexts or fluctuations. Extensive experiments verify the effectiveness of the proposed method, which obtains competitive accuracy on the two widely-used UDA benchmarks, i.e., 75.6 mIoU on GTA to Cityscapes and 68.2 mIoU on Synthia to Cityscapes. Moreover, our method is compatible with other UDA approaches to further improve the performance without introducing extra parameters.
View PDF Chat

Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark

2022-01-01
Jianwu Fang , Leilei Li , Kuan Yang +3 more
Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on … Traffic accident prediction in driving videos aims to provide an early warning of the accident occurrence, and supports the decision making of safe driving systems. Previous works usually concentrate on the spatial-temporal correlation of object-level context, while they do not fit the inherent long-tailed data distribution well and are vulnerable to severe environmental change. In this work, we propose a Cognitive Accident Prediction (CAP) method that explicitly leverages human-inspired cognition of text description on the visual observation and the driver attention to facilitate model training. In particular, the text description provides a dense semantic description guidance for the primary context of the traffic scene, while the driver attention provides a traction to focus on the critical region closely correlating with safe driving. CAP is formulated by an attentive text-to-vision shift fusion module, an attentive scene context transfer module, and the driver attention guided accident prediction module. We leverage the attention mechanism in these modules to explore the core semantic cues for accident prediction. In order to train CAP, we extend an existing self-collected DADA-2000 dataset (with annotated driver attention for each frame) with further factual text descriptions for the visual observations before the accidents. Besides, we construct a new large-scale benchmark consisting of 11,727 in-the-wild accident videos with over 2.19 million frames (named as CAP-DATA) together with labeled fact-effect-reason-introspection description and temporal accident frame label. Based on extensive experiments, the superiority of CAP is validated compared with state-of-the-art approaches. The code, CAP-DATA, and all results will be released in \url{https://github.com/JWFanggit/LOTVS-CAP}.
View PDF Chat

StepNet: Spatial-temporal Part-aware Network for Sign Language Recognition

2022-01-01
Shen Xiao-long , Zhedong Zheng , Yi Yang
The goal of sign language recognition (SLR) is to help those who are hard of hearing or deaf overcome the communication barrier. Most existing approaches can be typically divided into … The goal of sign language recognition (SLR) is to help those who are hard of hearing or deaf overcome the communication barrier. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. Skeleton-based methods do not consider facial expressions, while RGB-based approaches usually ignore the fine-grained hand structure. To overcome both limitations, we propose a new framework called Spatial-temporal Part-aware network~(StepNet), based on RGB parts. As its name suggests, it is made up of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Part-level Spatial Modeling, in particular, automatically captures the appearance-based properties, such as hands and faces, in the feature space without the use of any keypoint-level annotations. On the other hand, Part-level Temporal Modeling implicitly mines the long-short term context to capture the relevant attributes over time. Extensive experiments demonstrate that our StepNet, thanks to spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three commonly-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Additionally, the proposed method is compatible with the optical flow input and can produce superior performance if fused. For those who are hard of hearing, we hope that our work can act as a preliminary step.
View PDF Chat

Point Cloud Pre-training by Mixing and Disentangling

2021-09-01
Chao Sun , Zhedong Zheng , Xiaohan Wang +2 more
The annotation for large-scale point clouds is still time-consuming and unavailable for many real-world tasks. Point cloud pre-training is one potential solution for obtaining a scalable model for fast adaptation. … The annotation for large-scale point clouds is still time-consuming and unavailable for many real-world tasks. Point cloud pre-training is one potential solution for obtaining a scalable model for fast adaptation. Therefore, in this paper, we investigate a new self-supervised learning approach, called Mixing and Disentangling (MD), for point cloud pre-training. As the name implies, we explore how to separate the original point cloud from the mixed point cloud, and leverage this challenging task as a pretext optimization objective for model training. Considering the limited training data in the original dataset, which is much less than prevailing ImageNet, the mixing process can efficiently generate more high-quality samples. We build one baseline network to verify our intuition, which simply contains two modules, encoder and decoder. Given a mixed point cloud, the encoder is first pre-trained to extract the semantic embedding. Then an instance-adaptive decoder is harnessed to disentangle the point clouds according to the embedding. Albeit simple, the encoder is inherently able to capture the point cloud keypoints after training and can be fast adapted to downstream tasks including classification and segmentation by the pre-training and fine-tuning paradigm. Extensive experiments on two datasets show that the encoder + ours (MD) significantly surpasses that of the encoder trained from scratch and converges quickly. In ablation studies, we further study the effect of each component and discuss the advantages of the proposed self-supervised learning strategy. We hope this self-supervised learning attempt on point clouds can pave the way for reducing the deeply-learned model dependence on large-scale labeled data and saving a lot of annotation costs in the future.
View PDF Chat

Connecting Language and Vision for Natural Language-Based Vehicle Retrieval

2021-06-01
Shuai Bai , Zhedong Zheng , Xiaohan Wang +5 more
Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing prac-tices focus on the image-based vehicle matching, including vehicle re-identification and … Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing prac-tices focus on the image-based vehicle matching, including vehicle re-identification and vehicle tracking. In this paper, we apply one new modality, i.e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario. The natural language-based vehicle search poses one new challenge of fine-grained understanding of both vision and language modalities. To connect language and vision, we propose to jointly train the state-of-the-art vision models with the transformer-based language model in an end-to-end manner. Except for the network structure design and the training strategy, several optimization objectives are also revisited in this work. The qualitative and quantitative experiments verify the effectiveness of the proposed method. Our proposed method has achieved the 1st place on the 5th AI City Challenge, yielding competitive performance 18.69% MRR accuracy on the private test set. We hope this work can pave the way for the future study on using language description effectively and efficiently for real-world vehicle retrieval systems. The code will be available at https://github.com/ShuaiBai623/AIC2021-T5-CLV.
View PDF Chat

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

2021-05-18
Chuchu Han , Zhedong Zheng , Changxin Gao +2 more
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and … The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.
View PDF Chat

Each Part Matters: Local Patterns Facilitate Cross-View Geo-Localization

2021-02-23
Tingyu Wang , Zhedong Zheng , Chenggang Yan +4 more
Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by … Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations. Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas. In this work, we argue that neighbor areas can be leveraged as auxiliary information, enriching discriminative clues for geolocalization. Specifically, we introduce a simple and effective deep neural network, called Local Pattern Network (LPN), to take advantage of contextual information in an end-to-end manner. Without using extra part estimators, LPN adopts a square-ring feature partition strategy, which provides the attention according to the distance to the image center. It eases the part matching and enables the part-wise representation learning. Owing to the square-ring partition design, the proposed LPN has good scalability to rotation variations and achieves competitive results on three prevailing benchmarks, i.e., University-1652, CVUSA and CVACT. Besides, we also show the proposed LPN can be easily embedded into other frameworks to further boost performance.
View PDF Chat

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

2021-01-06
Zhedong Zheng , Yi Yang
View PDF Chat

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

2021-01-01
Chuchu Han , Zhedong Zheng , Changxin Gao +2 more
The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and … The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods.
View PDF Chat

Less is More: Sparse Sampling for Dense Reaction Predictions

2021-01-01
Kezhou Lin , Xiaohan Wang , Zhedong Zheng +2 more
Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our … Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience. In this report, we present our method for 2021 Evoked Expression from Videos Challenge. In particular, our model utilizes both audio and image modalities as inputs to predict emotion changes of viewers. To model long-range emotion changes, we use a GRU-based model to predict one sparse signal with 1Hz. We observe that the emotion changes are smooth. Therefore, the final dense prediction is obtained via linear interpolating the signal, which is robust to the prediction fluctuation. Albeit simple, the proposed method has achieved pearson's correlation score of 0.04430 on the final private test set.

Connecting Language and Vision for Natural Language-Based Vehicle Retrieval

2021-01-01
Shuai Bai , Zhedong Zheng , Xiaohan Wang +5 more
Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle re-identification and … Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing practices focus on the image-based vehicle matching, including vehicle re-identification and vehicle tracking. In this paper, we apply one new modality, i.e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario. The natural language-based vehicle search poses one new challenge of fine-grained understanding of both vision and language modalities. To connect language and vision, we propose to jointly train the state-of-the-art vision models with the transformer-based language model in an end-to-end manner. Except for the network structure design and the training strategy, several optimization objectives are also re-visited in this work. The qualitative and quantitative experiments verify the effectiveness of the proposed method. Our proposed method has achieved the 1st place on the 5th AI City Challenge, yielding competitive performance 18.69% MRR accuracy on the private test set. We hope this work can pave the way for the future study on using language description effectively and efficiently for real-world vehicle retrieval systems. The code will be available at https://github.com/ShuaiBai623/AIC2021-T5-CLV.
View PDF Chat
Coauthor Papers Together
Yi Yang 47
Liang Zheng 16
Tat‐Seng Chua 13
Xiaohan Wang 10
Chenggang Yan 6
Bingwen Hu 5
Bang Zhang 4
Yaxiong Wang 4
Mingliang Xu 4
Ping Liu 4
Zhun Zhong 3
Yunchao Wei 3
Yaoqi Sun 3
Tingyu Wang 3
Mingwu Ren 3
Ruiyang Zhang 2
Michael Garrett 2
Shuai Bai 2
Wankou Yang 2
Junyang Lin 2
Xiaodong Yang 2
Yi-Dong Shen 2
Jianru Xue 2
Pan Pan 2
Changxin Gao 2
Tao Guan 2
Chuchu Han 2
Yi Yang 2
Tingyu Wang 2
Chang Zhou 2
Zhu Li 2
Yinan Zhou 2
Shuyu Yang 2
Hongxia Yang 2
Zhu Zhang 2
Yucheng Suo 2
Linchao Zhu 2
Daiheng Gao 2
Yawei Luo 2
Zhilan Hu 2
Jianwu Fang 2
Xuanmeng Zhang 2
Leigang Qu 2
Zhiding Yu 2
Jan Kautz 2
Hang Yu 2
Bolun Zheng 2
Shaozi Li 2
Junqing Yu 2
Xu Zhang 2