Rui Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rui Yang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Xiu Li
Tsinghua University
4 shared publications - Hantao Zhou
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
2 shared publications - Runze Hu
School of Information and Electronics, Beijing Institute of Technology, Beijing, China
2 shared publications - Chang Shu
School of Computer Science, University of Nottingham Ningbo China, Ningbo, China
1 shared publication - Hailong Ma
Bytedance Inc
1 shared publication - Haoran Duan
Department of Automation, Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 9565-9576
UniHead: Unifying Multi-Perception for Detection Heads
The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual capabilities, such as deformation perception (DP), global perception (GP), and cross-task perception (CTP). Despite numerous methods attempting to enhance these abilities from a single aspect, achieving a comprehensive and unified solution remains a significant challenge. In response to this challenge, we develop an innovative detection head, termed UniHead, to unify three perceptual abilities simultaneously. More precisely, our approach: 1) introduces DP, enabling the model to adaptively sample object features; 2) proposes a dual-axial aggregation transformer (DAT) to adeptly model long-range dependencies, thereby achieving GP; and 3) devises a cross-task interaction transformer (CIT) that facilitates interaction between the classification and localization branches, thus aligning the two tasks. As a plug-and-play method, the proposed UniHead can be conveniently integrated with existing detectors. Extensive experiments on the COCO dataset demonstrate that our UniHead can bring significant improvements to many detectors. For instance, the UniHead can obtain $+$ 2.7 AP gains in RetinaNet, $+$ 2.9 AP gains in FreeAnchor, and $+$ 2.1 AP gains in GFL. The code is available at https://github.com/zht8506/UniHead.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (5) , 9565-9576
UniHead: Unifying Multi-Perception for Detection Heads
The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization functions. Regrettably, the commonly used parallel head often lacks omni perceptual capabilities, such as deformation perception (DP), global perception (GP), and cross-task perception (CTP). Despite numerous methods attempting to enhance these abilities from a single aspect, achieving a comprehensive and unified solution remains a significant challenge. In response to this challenge, we develop an innovative detection head, termed UniHead, to unify three perceptual abilities simultaneously. More precisely, our approach: 1) introduces DP, enabling the model to adaptively sample object features; 2) proposes a dual-axial aggregation transformer (DAT) to adeptly model long-range dependencies, thereby achieving GP; and 3) devises a cross-task interaction transformer (CIT) that facilitates interaction between the classification and localization branches, thus aligning the two tasks. As a plug-and-play method, the proposed UniHead can be conveniently integrated with existing detectors. Extensive experiments on the COCO dataset demonstrate that our UniHead can bring significant improvements to many detectors. For instance, the UniHead can obtain $+$ 2.7 AP gains in RetinaNet, $+$ 2.9 AP gains in FreeAnchor, and $+$ 2.1 AP gains in GFL. The code is available at https://github.com/zht8506/UniHead.
- 22 September 2023
- Published by Springer Nature
- p. 232-243
GH-QFL: Enhancing Industrial Defect Detection Through Hard Example Mining
- 22 September 2023
- Published by Springer Nature
- p. 232-243
GH-QFL: Enhancing Industrial Defect Detection Through Hard Example Mining
- 23 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
ETDNet: Efficient Transformer-Based Detection Network for Surface Defect Detection
Deep learning-based surface defect detectors play a crucial role in ensuring product quality during inspection processes. However, accurately and efficiently detecting defects remains challenging due to specific characteristics inherent in defective images, involving a high degree of foreground-background similarity, scale variation, and shape variation. To address this challenge, we propose an efficient Transformer-based detection network, ETDNet, consisting of three novel designs to achieve superior performance. Firstly, ETDNet takes a lightweight Vision Transformer to extract representative global features. This approach ensures an accurate feature characterization of defects even with similar backgrounds. Secondly, a channel-modulated feature pyramid network (CM-FPN) is devised to fuse multi-level features and maintain critical information from corresponding levels. Lastly, a novel task-oriented decoupled (TOD) head is introduced to tackle inconsistent representation between classification and regression tasks. The TOD head employs a local feature representation module to learn object-aware local features and introduces a global feature representation module, based on the attention mechanism, to learn content-aware global features. By integrating these two modules into the head, ETDNet can effectively classify and perceive defects with varying shapes and scales. Extensive experiments on various defect detection datasets demonstrate the effectiveness of the proposed ETDNet. For instance, it achieves AP 46.7% (v.s. 45.9%), and AP 50 80.2% (v.s. 79.1%) with 49 FPS on NeU-DET. Code is available at https://github.com/zht8506/ETDNet.
- 23 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-14
ETDNet: Efficient Transformer-Based Detection Network for Surface Defect Detection
Deep learning-based surface defect detectors play a crucial role in ensuring product quality during inspection processes. However, accurately and efficiently detecting defects remains challenging due to specific characteristics inherent in defective images, involving a high degree of foreground-background similarity, scale variation, and shape variation. To address this challenge, we propose an efficient Transformer-based detection network, ETDNet, consisting of three novel designs to achieve superior performance. Firstly, ETDNet takes a lightweight Vision Transformer to extract representative global features. This approach ensures an accurate feature characterization of defects even with similar backgrounds. Secondly, a channel-modulated feature pyramid network (CM-FPN) is devised to fuse multi-level features and maintain critical information from corresponding levels. Lastly, a novel task-oriented decoupled (TOD) head is introduced to tackle inconsistent representation between classification and regression tasks. The TOD head employs a local feature representation module to learn object-aware local features and introduces a global feature representation module, based on the attention mechanism, to learn content-aware global features. By integrating these two modules into the head, ETDNet can effectively classify and perceive defects with varying shapes and scales. Extensive experiments on various defect detection datasets demonstrate the effectiveness of the proposed ETDNet. For instance, it achieves AP 46.7% (v.s. 45.9%), and AP 50 80.2% (v.s. 79.1%) with 49 FPS on NeU-DET. Code is available at https://github.com/zht8506/ETDNet.
- 6 November 2022
- Published by Springer Nature
- p. 480-496
ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer
- 6 November 2022
- Published by Springer Nature
- p. 480-496
ScalableViT: Rethinking the Context-Oriented Generalization of Vision Transformer
- Open Access
- 18 October 2022
- Published by Elsevier in Image and Vision Computing
- Vol. 128, 104570
ArCo: Attention-reinforced transformer with contrastive learning for image captioning
- 18 October 2022
- Published by Elsevier in Image and Vision Computing
- Vol. 128, 104570
Open AccessArCo: Attention-reinforced transformer with contrastive learning for image captioning