Shifeng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Shifeng Zhang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Stan Z. Li
Institute of Automation NLPR Chinese Academy of Sciences Beijing China
9 shared publications - Zhen Lei
Chinese Academy of Sciences
9 shared publications - Jun Wan
Institute of Automation, Chinese Academy of Sciences, Beijing, China, China
4 shared publications Stan Z. Li
Westlake University, Hangzhou, CHINA
4 shared publications- Xiaobo Wang
JD AI Research Beijing China
4 shared publications - Hailin Shi
NIO, Beijing, China
3 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2576-2585
AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2576-2585
Open AccessAeroDuo: Aerial Duo for UAV-based Vision and Language Navigation
- Open Access
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to $50.7\%$ AP without introducing any overhead. The code is available at https://github.com/sfzhang15/ATSSOpen AccessBridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to $50.7\%$ AP without introducing any overhead. The code is available at https://github.com/sfzhang15/ATSS - 25 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 43  (11) , 4008-4020
RefineFace: Refinement Neural Network for High Performance Face Detection
Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists many tiny faces. In this paper, we present a single-shot refinement face detector namely RefineFace to achieve high performance. Specifically, it consists of five modules: selective two-step regression (STR), selective two-step classification (STC), scale-aware margin loss (SML), feature supervision module (FSM) and receptive field enhancement (RFE). To enhance the regression ability for high location accuracy, STR coarsely adjusts locations and sizes of anchors from high level detection layers to provide better initialization for subsequent regressor. To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification. Besides, RFE is presented to provide more diverse receptive field to better capture faces in some extreme poses. Extensive experiments conducted on WIDER FACE, AFW, PASCAL Face, FDDB, MAFA demonstrate that our method achieves state-of-the-art results and runs at 37.3 FPS with ResNet-18 for VGA-resolution images.
- 25 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 43  (11) , 4008-4020
RefineFace: Refinement Neural Network for High Performance Face Detection
Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists many tiny faces. In this paper, we present a single-shot refinement face detector namely RefineFace to achieve high performance. Specifically, it consists of five modules: selective two-step regression (STR), selective two-step classification (STC), scale-aware margin loss (SML), feature supervision module (FSM) and receptive field enhancement (RFE). To enhance the regression ability for high location accuracy, STR coarsely adjusts locations and sizes of anchors from high level detection layers to provide better initialization for subsequent regressor. To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification. Besides, RFE is presented to provide more diverse receptive field to better capture faces in some extreme poses. Extensive experiments conducted on WIDER FACE, AFW, PASCAL Face, FDDB, MAFA demonstrate that our method achieves state-of-the-art results and runs at 37.3 FPS with ResNet-18 for VGA-resolution images.
- 7 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31  (2) , 674-687
RefineDet++: Single-Shot Refinement Neural Network for Object Detection
Convolutional neural network based methods have dominated object detection in recent years, which can be divided into the one-stage approach and the two-stage approach. In general, the two-stage approach ( e.g., Faster R-CNN) achieves high accuracy, while the one-stage approach ( e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, we propose a novel single-shot based detector, namely RefineDet++, which achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. The proposed RefineDet++ consists of two inter-connected modules: the anchor refinement module and the alignment detection module. Specifically, the former module aims to (1) filter out negative anchors to reduce search space for the subsequent classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes (1) the refined anchors as the input from the former module with (2) a newly designed alignment convolution operation to further improve the regression accuracy and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC and MS COCO demonstrate that RefineDet++ achieves state-of-the-art detection accuracy with high efficiency.
- 7 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31  (2) , 674-687
RefineDet++: Single-Shot Refinement Neural Network for Object Detection
Convolutional neural network based methods have dominated object detection in recent years, which can be divided into the one-stage approach and the two-stage approach. In general, the two-stage approach ( e.g., Faster R-CNN) achieves high accuracy, while the one-stage approach ( e.g., SSD) has the advantage of high efficiency. To inherit the merits of both while overcoming their disadvantages, we propose a novel single-shot based detector, namely RefineDet++, which achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. The proposed RefineDet++ consists of two inter-connected modules: the anchor refinement module and the alignment detection module. Specifically, the former module aims to (1) filter out negative anchors to reduce search space for the subsequent classifier, and (2) coarsely adjust the locations and sizes of anchors to provide better initialization for the subsequent regressor. The latter module takes (1) the refined anchors as the input from the former module with (2) a newly designed alignment convolution operation to further improve the regression accuracy and predict multi-class label. Meanwhile, we design a transfer connection block to transfer the features in the anchor refinement module to predict locations, sizes and class labels of objects in the object detection module. The multi-task loss function enables us to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC and MS COCO demonstrate that RefineDet++ achieves state-of-the-art detection accuracy with high efficiency.
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 2  (2) , 182-193
CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing
Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects (≤170) and modalities (≤2), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities. Specifically, it consists of 1,000 subjects with 21,000 videos and each sample has 3 modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing. Moreover, we present a novel multi-modal multi-scale fusion method as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/face-anti-spoofing/welcome/challengecvpr2019?authuser=0.
- 12 February 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 2  (2) , 182-193
CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing
Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects (≤170) and modalities (≤2), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities. Specifically, it consists of 1,000 subjects with 21,000 videos and each sample has 3 modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing. Moreover, we present a novel multi-modal multi-scale fusion method as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/face-anti-spoofing/welcome/challengecvpr2019?authuser=0.
- Open Access
Mis-classified Vector Guided Softmax Loss for Face Recognition
Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (\textit{e.g.}, angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives.
Open AccessMis-classified Vector Guided Softmax Loss for Face Recognition
Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (\textit{e.g.}, angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives.
- 1 October 2019
- Published by Elsevier in Neurocomputing
- Vol. 364, 297-309
Faceboxes: A CPU real-time and accurate unconstrained face detector
- 1 October 2019
- Published by Elsevier in Neurocomputing
- Vol. 364, 297-309
Faceboxes: A CPU real-time and accurate unconstrained face detector
- 16 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 22  (2) , 380-393
WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Pedestrian detection has achieved significant progress with the availability of exiting benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; 2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of 13,382 images with 399,359 annotations, i.e., 29.84 annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates.
- 16 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 22  (2) , 380-393
WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Pedestrian detection has achieved significant progress with the availability of exiting benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; 2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of 13,382 images with 399,359 annotations, i.e., 29.84 annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates.
- 5 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 50  (3) , 1292-1305
Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis
Deep multitask learning for face analysis has received increasing attentions. From literature, most existing methods focus on optimizing a main task by jointly learning several auxiliary tasks. It is challenging to consider the performance of each task in a multitask framework due to the following reasons: 1) different face tasks usually rely on different levels of semantic features; 2) each task has different learning convergence rate, which could affect the whole performance when joint training; and 3) multitask model needs rich label information for efficient training, but existing facial datasets provide limited annotations. To address these issues, we propose a task-oriented feature-fused network (TFN) for simultaneously solving face detection, landmark localization, and attribute analysis. In this network, a task-oriented feature-fused block is designed to learn task-specific feature combinations; then, an alternative multitask training scheme is presented to optimize each task with considering of their different learning capacities. We also present a large-scale face dataset called JFA in support of proposed method, which provides multivariate labels, including face bounding box, 68 facial landmarks, and 3 attribute labels (i.e., apparent age, gender, and ethnicity). The experimental results suggest that the TFN outperforms several multitask models on the JFA dataset. Furthermore, our approach achieves competitive performances on WIDER FACE and 300W dataset, and obtains state-of-the-art results for gender recognition on the MORPH II dataset.
- 5 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 50  (3) , 1292-1305
Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis
Deep multitask learning for face analysis has received increasing attentions. From literature, most existing methods focus on optimizing a main task by jointly learning several auxiliary tasks. It is challenging to consider the performance of each task in a multitask framework due to the following reasons: 1) different face tasks usually rely on different levels of semantic features; 2) each task has different learning convergence rate, which could affect the whole performance when joint training; and 3) multitask model needs rich label information for efficient training, but existing facial datasets provide limited annotations. To address these issues, we propose a task-oriented feature-fused network (TFN) for simultaneously solving face detection, landmark localization, and attribute analysis. In this network, a task-oriented feature-fused block is designed to learn task-specific feature combinations; then, an alternative multitask training scheme is presented to optimize each task with considering of their different learning capacities. We also present a large-scale face dataset called JFA in support of proposed method, which provides multivariate labels, including face bounding box, 68 facial landmarks, and 3 attribute labels (i.e., apparent age, gender, and ethnicity). The experimental results suggest that the TFN outperforms several multitask models on the JFA dataset. Furthermore, our approach achieves competitive performances on WIDER FACE and 300W dataset, and obtains state-of-the-art results for gender recognition on the MORPH II dataset.
- Open Access
ScratchDet: Training Single-Shot Object Detectors from Scratch
Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) The classification and detection have different degrees of sensitivity to translation, resulting in the learning objective bias; 2) The architecture is limited by the classification network, leading to the inconvenience of modification. To cope with these problems, training detectors from scratch is a feasible solution. However, the detectors trained from scratch generally perform worse than the pretrained ones, even suffer from the convergence issue in training. In this paper, we explore to train object detectors from scratch robustly. By analysing the previous work on optimization landscape, we find that one of the overlooked points in current trained-from-scratch detector is the BatchNorm. Resorting to the stable and predictable gradient brought by BatchNorm, detectors can be trained from scratch stably while keeping the favourable performance independent to the network architecture. Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence. By extensive experiments and analyses on downsampling factor, we propose the Root-ResNet backbone network, which makes full use of the information from original images. Our ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods. Codes will be made publicly available at https://github.com/KimSoybean/ScratchDet.
Open AccessScratchDet: Training Single-Shot Object Detectors from Scratch
Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) The classification and detection have different degrees of sensitivity to translation, resulting in the learning objective bias; 2) The architecture is limited by the classification network, leading to the inconvenience of modification. To cope with these problems, training detectors from scratch is a feasible solution. However, the detectors trained from scratch generally perform worse than the pretrained ones, even suffer from the convergence issue in training. In this paper, we explore to train object detectors from scratch robustly. By analysing the previous work on optimization landscape, we find that one of the overlooked points in current trained-from-scratch detector is the BatchNorm. Resorting to the stable and predictable gradient brought by BatchNorm, detectors can be trained from scratch stably while keeping the favourable performance independent to the network architecture. Taking this advantage, we are able to explore various types of networks for object detection, without suffering from the poor convergence. By extensive experiments and analyses on downsampling factor, we propose the Root-ResNet backbone network, which makes full use of the information from original images. Our ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods. Codes will be made publicly available at https://github.com/KimSoybean/ScratchDet.