Xueyan Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xueyan Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Keyan Wang
Key Laboratory of Integrated Service Networks, Xidian University, Xian, China
1 shared publication Liyun Yang
State Key Laboratory of lntegrated Services Networks (ISN), Xidian University, Xian, China
1 shared publication- Peicheng Zhou
State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xian, China
1 shared publication - Rui Zhang
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, China
1 shared publication - Yunsong Li
Xidian University, Xi'an, Shaanxi, CHINA
1 shared publication - Zuntian Chen
Xian Institute Electromechanical Information Technology, Xian, China
1 shared publication
Latest Publications
- Open Access
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 4208-4221
AFE-Net: Attention-Guided Feature Enhancement Network for Infrared Small Target Detection
Infrared small target detection is considerably challenging due to the few pixels in targets, low signal-to-noise ratio, and complex background. In this paper, we propose an effective Attention-guided Feature Enhancement Network (AFE-Net) which can leverage the local and non-local features of targets and background in infrared images. The AFE-Net consists of three key modules, namely encoder and decoder interactive guidance (EDIG) module, cascading false alarm removal (CFAR) module, and random scale input (RSI) module. Specifically, in the EDIG module, we employ a channel attention mechanism on encoding and decoding layers to select feature channels with higher contribution. Then, we impose a bottom-up point-wise attention block to highlight the features of small infrared targets and suppress possible noise by incorporating the low-level detailed features into the high-level semantic features. The CFAR module extracts affluent global features by cascading non-local operations of different layers, which can remove clutters with similar features to infrared targets. The RSI module is placed in front of the entire detection network to extract multi-scale features of infrared small targets, which can enhance the robustness of the proposed network. Experimental results on the SIRST dataset and comprehensive comparisons with representative methods demonstrate the superiority of our proposed method.
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 4208-4221
Open AccessAFE-Net: Attention-Guided Feature Enhancement Network for Infrared Small Target Detection
Infrared small target detection is considerably challenging due to the few pixels in targets, low signal-to-noise ratio, and complex background. In this paper, we propose an effective Attention-guided Feature Enhancement Network (AFE-Net) which can leverage the local and non-local features of targets and background in infrared images. The AFE-Net consists of three key modules, namely encoder and decoder interactive guidance (EDIG) module, cascading false alarm removal (CFAR) module, and random scale input (RSI) module. Specifically, in the EDIG module, we employ a channel attention mechanism on encoding and decoding layers to select feature channels with higher contribution. Then, we impose a bottom-up point-wise attention block to highlight the features of small infrared targets and suppress possible noise by incorporating the low-level detailed features into the high-level semantic features. The CFAR module extracts affluent global features by cascading non-local operations of different layers, which can remove clutters with similar features to infrared targets. The RSI module is placed in front of the entire detection network to extract multi-scale features of infrared small targets, which can enhance the robustness of the proposed network. Experimental results on the SIRST dataset and comprehensive comparisons with representative methods demonstrate the superiority of our proposed method.