Xin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xin Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Boyang Li
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Chao Xiao
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Miao Li
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Nuo Chen
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Ruojing Li
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication - Wei An
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
1 shared publication
Latest Publications
- Open Access
- 1 May 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (9) , 1397
Semantic Density-Guided ResNet for Dense Infrared Small Target Detection
Dense infrared small target detection (ISTD) in long-range remote sensing is critical for multi-target surveillance, yet existing benchmarks mostly contain only sparsely distributed targets and rarely reflect dense scenes. To address this limitation, we construct a new dense satellite ISTD dataset, IR-SatDense, by compositing small targets onto real satellite infrared backgrounds and partitioning it into subsets using the Average Minimum Inter-Target Distance (AMID) to explicitly control target density. By visualizing multi-stage backbone features, we observe that in dense scenes the deepest stage naturally forms compact, high-response target clusters in the semantic feature maps, while low- and middle-level features remain heavily cluttered. This motivates us to treat high-level semantic density as a global prior to guide low-level feature enhancement. Therefore, we propose Semantic Density-Guided ResNet (SDG-ResNet), a plug-in backbone that attaches a lightweight semantic density head to the deepest stage and injects the predicted density map into intermediate layers through Semantic Density-Guided Refine (SDGR) blocks with residual spatial gating. Integrated into representative transformer-based detectors, including Deformable DETR, DETA, and DINO, SDG-ResNet consistently improves the probability of detection (PD) at comparable false alarm (FA) levels on IR-SatDense while maintaining competitive performance on the sparse dataset IRSTD-1K.
- 1 May 2026
- Published by MDPI AG in Remote Sensing
- Vol. 18 (9) , 1397
Open AccessSemantic Density-Guided ResNet for Dense Infrared Small Target Detection
Dense infrared small target detection (ISTD) in long-range remote sensing is critical for multi-target surveillance, yet existing benchmarks mostly contain only sparsely distributed targets and rarely reflect dense scenes. To address this limitation, we construct a new dense satellite ISTD dataset, IR-SatDense, by compositing small targets onto real satellite infrared backgrounds and partitioning it into subsets using the Average Minimum Inter-Target Distance (AMID) to explicitly control target density. By visualizing multi-stage backbone features, we observe that in dense scenes the deepest stage naturally forms compact, high-response target clusters in the semantic feature maps, while low- and middle-level features remain heavily cluttered. This motivates us to treat high-level semantic density as a global prior to guide low-level feature enhancement. Therefore, we propose Semantic Density-Guided ResNet (SDG-ResNet), a plug-in backbone that attaches a lightweight semantic density head to the deepest stage and injects the predicted density map into intermediate layers through Semantic Density-Guided Refine (SDGR) blocks with residual spatial gating. Integrated into representative transformer-based detectors, including Deformable DETR, DETA, and DINO, SDG-ResNet consistently improves the probability of detection (PD) at comparable false alarm (FA) levels on IR-SatDense while maintaining competitive performance on the sparse dataset IRSTD-1K.