Quan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Quan Zhang has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jianhuang Lai
Sun Yat-Sen University, Guangzhou, China
6 shared publications - Xiaohua Xie
Sun Yat-Sen University, Guangzhou, China
5 shared publications - Zhanxiang Feng
Sun Yat-sen University
2 shared publications - Hong Wu
Sun Yat-sen University
1 shared publication - Hongbo Chen
Sun Yat-sen University
1 shared publication - Hongfei Suo
Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration, School of Automation, Harbin University of Science and Technology, Harbin 150080, China
1 shared publication
Latest Publications
- 9 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 327
RDPA: A concealed and perilous physical adversarial attack for nighttime traffic signs recognition
- 9 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 327
RDPA: A concealed and perilous physical adversarial attack for nighttime traffic signs recognition
- 5 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
Unsupervised group re-identification from aerial perspective via strategic member harmonization
- 5 March 2025
- Published by Elsevier in Pattern Recognition
- Vol. 164
Unsupervised group re-identification from aerial perspective via strategic member harmonization
- Open Access
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://github.com/LinlyAC/VDT-AGPReID
Open AccessView-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
Existing person re-identification methods have achieved remarkable advances in appearance-based identity association across homogeneous cameras, such as ground-ground matching. However, as a more practical scenario, aerial-ground person re-identification (AGPReID) among heterogeneous cameras has received minimal attention. To alleviate the disruption of discriminative identity representation by dramatic view discrepancy as the most significant challenge in AGPReID, the view-decoupled transformer (VDT) is proposed as a simple yet effective framework. Two major components are designed in VDT to decouple view-related and view-unrelated features, namely hierarchical subtractive separation and orthogonal loss, where the former separates these two features inside the VDT, and the latter constrains these two to be independent. In addition, we contribute a large-scale AGPReID dataset called CARGO, consisting of five/eight aerial/ground cameras, 5,000 identities, and 108,563 images. Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5.0%/2.7% on CARGO and 3.7%/5.2% on AG-ReID, keeping the same magnitude of computational complexity. Our project is available at https://github.com/LinlyAC/VDT-AGPReID
- 29 October 2023
- Published by Springer Nature
- p. 180-191
TANet: Adversarial Network via Tokens Transformer for Universal Domain Adaptation
- 29 October 2023
- Published by Springer Nature
- p. 180-191
TANet: Adversarial Network via Tokens Transformer for Universal Domain Adaptation
- 25 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4517-4528
Wavelet-Guided Promotion-Suppression Transformer for Surface-Defect Detection
Surface-defect detection aims to accurately locate and classify defect areas in images via pixel-level annotations. Different from the objects in traditional image segmentation, defect areas comprise a small group of pixels with random shapes, characterized by uncommon textures and edges that are inconsistent with the normal surface patterns of industrial products. This task-specific knowledge is hardly considered in the current methods. Therefore, we propose a two-stage “promotion-suppression” transformer (PST) framework, which explicitly adopts the wavelet features to guide the network to focus on the detailed features in the images. Specifically, in the promotion stage, we propose the Haar augmentation module to improve the backbone’s sensitivity to high-frequency details. However, the background noise is inevitably amplified as well because it also constitutes high-frequency information. Therefore, a quadratic feature-fusion module (QFFM) is proposed in the suppression stage, which exploits the two properties of noise: independence and attenuation. The QFFM analyzes the similarities and differences between noise and defect features to achieve noise suppression. Compared with the traditional linear-fusion approach, the QFFM is more sensitive to high-frequency details; thus, it can afford highly discriminative features. Extensive experiments are conducted on three datasets, namely DAGM, MT, and CRACK500, which demonstrate the superiority of the proposed PST framework.
- 25 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32 (10577149) , 4517-4528
Wavelet-Guided Promotion-Suppression Transformer for Surface-Defect Detection
Surface-defect detection aims to accurately locate and classify defect areas in images via pixel-level annotations. Different from the objects in traditional image segmentation, defect areas comprise a small group of pixels with random shapes, characterized by uncommon textures and edges that are inconsistent with the normal surface patterns of industrial products. This task-specific knowledge is hardly considered in the current methods. Therefore, we propose a two-stage “promotion-suppression” transformer (PST) framework, which explicitly adopts the wavelet features to guide the network to focus on the detailed features in the images. Specifically, in the promotion stage, we propose the Haar augmentation module to improve the backbone’s sensitivity to high-frequency details. However, the background noise is inevitably amplified as well because it also constitutes high-frequency information. Therefore, a quadratic feature-fusion module (QFFM) is proposed in the suppression stage, which exploits the two properties of noise: independence and attenuation. The QFFM analyzes the similarities and differences between noise and defect features to achieve noise suppression. Compared with the traditional linear-fusion approach, the QFFM is more sensitive to high-frequency details; thus, it can afford highly discriminative features. Extensive experiments are conducted on three datasets, namely DAGM, MT, and CRACK500, which demonstrate the superiority of the proposed PST framework.
- 3 November 2022
- Published by Springer Nature
- p. 433-443
Salient Foreground-Aware Network for Person Search
- 3 November 2022
- Published by Springer Nature
- p. 433-443
Salient Foreground-Aware Network for Person Search
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 352-365
Seeing Like a Human: Asynchronous Learning With Dynamic Progressive Refinement for Person Re-Identification
Learning discriminative and rich features is an important research task for person re-identification. Previous studies have attempted to capture global and local features at the same time and layer of the model in a non-interactive manner, which are called synchronous learning. However, synchronous learning leads to high similarity, and further defects in model performance. To this end, we propose asynchronous learning based on the human visual perception mechanism. Asynchronous learning emphasizes the time asynchrony and space asynchrony of feature learning and achieves mutual promotion and cyclical interaction for feature learning. Furthermore, we design a dynamic progressive refinement module to improve local features with the guidance of global features. The dynamic property allows this module to adaptively adjust the network parameters according to the input image, in both the training and testing stage. The progressive property narrows the semantic gap between the global and local features, which is due to the guidance of global features. Finally, we have conducted several experiments on four datasets, including Market1501, CUHK03, DukeMTMC-ReID, and MSMT17. The experimental results show that asynchronous learning can effectively improve feature discrimination and achieve strong performance.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 352-365
Seeing Like a Human: Asynchronous Learning With Dynamic Progressive Refinement for Person Re-Identification
Learning discriminative and rich features is an important research task for person re-identification. Previous studies have attempted to capture global and local features at the same time and layer of the model in a non-interactive manner, which are called synchronous learning. However, synchronous learning leads to high similarity, and further defects in model performance. To this end, we propose asynchronous learning based on the human visual perception mechanism. Asynchronous learning emphasizes the time asynchrony and space asynchrony of feature learning and achieves mutual promotion and cyclical interaction for feature learning. Furthermore, we design a dynamic progressive refinement module to improve local features with the guidance of global features. The dynamic property allows this module to adaptively adjust the network parameters according to the input image, in both the training and testing stage. The progressive property narrows the semantic gap between the global and local features, which is due to the guidance of global features. Finally, we have conducted several experiments on four datasets, including Market1501, CUHK03, DukeMTMC-ReID, and MSMT17. The experimental results show that asynchronous learning can effectively improve feature discrimination and achieve strong performance.
- 17 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 8019-8033
Learning Modal-Invariant Angular Metric by Cyclic Projection Network for VIS-NIR Person Re-Identification
Person re-identification across visible and near-infrared cameras (VIS-NIR Re-ID) has widespread applications. The challenge of this task lies in heterogeneous image matching. Existing methods attempt to learn discriminative features via complex feature extraction strategies. Nevertheless, the distributions of visible and near-infrared features are disparate caused by modal gap, which significantly affects feature metric and makes the performance of the existing models poor. To address this problem, we propose a novel approach from the perspective of metric learning. We conduct metric learning on a well-designed angular space. Geometrically, features are mapped from the original space to the hypersphere manifold, which eliminates the variations of feature norm and concentrates on the angle between the feature and the target category. Specifically, we propose a cyclic projection network (CPN) that transforms features into an angle-related space while identity information is preserved. Furthermore, we proposed three kinds of loss functions, AICAL, LAL and DAL, in angular space for angular metric learning. Multiple experiments on two existing public datasets, SYSU-MM01 and RegDB, show that performance of our method greatly exceeds the SOTA performance.
- 17 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 8019-8033
Learning Modal-Invariant Angular Metric by Cyclic Projection Network for VIS-NIR Person Re-Identification
Person re-identification across visible and near-infrared cameras (VIS-NIR Re-ID) has widespread applications. The challenge of this task lies in heterogeneous image matching. Existing methods attempt to learn discriminative features via complex feature extraction strategies. Nevertheless, the distributions of visible and near-infrared features are disparate caused by modal gap, which significantly affects feature metric and makes the performance of the existing models poor. To address this problem, we propose a novel approach from the perspective of metric learning. We conduct metric learning on a well-designed angular space. Geometrically, features are mapped from the original space to the hypersphere manifold, which eliminates the variations of feature norm and concentrates on the angle between the feature and the target category. Specifically, we propose a cyclic projection network (CPN) that transforms features into an angle-related space while identity information is preserved. Furthermore, we proposed three kinds of loss functions, AICAL, LAL and DAL, in angular space for angular metric learning. Multiple experiments on two existing public datasets, SYSU-MM01 and RegDB, show that performance of our method greatly exceeds the SOTA performance.