Yuxin Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuxin Hu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Bin Gao
Key Laboratory of Technology in Geo-Spatial Information Processing and Application System and Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
1 shared publication- Bing Han
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
1 shared publication - Di Yin
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication - Guangyao Zhou
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
1 shared publication Guangyu Zhao
Key Laboratory of Technology in Geo-Spatial Information Processing and Application System and Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
1 shared publicationGuogang Yan
Key Laboratory of Technology in Geo-Spatial Information Processing and Application System and Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-22
Uni-RSNet: A Unified Recognition-Sorting Framework for SAR Interference Signals in Complex Electromagnetic Environments
Synthetic aperture radar (SAR) often receives interference from multiple emitters operating within the same frequency band. These interference signals are densely overlapped in time and frequency domains and strongly coupled with SAR echoes, which substantially increases the difficulty of signal recognition and sorting. In conventional processing chains, recognition and sorting are treated as independent modules with task-specific inputs, resulting in severe information fragmentation and cumulative-error propagation under dense interference conditions. To address these limitations, this paper proposes a unified recognition-sorting network for overlapping SAR interference signals, termed Uni-RSNet. Based on continuous multi-frame time-frequency representations, Uni-RSNet jointly captures high-dimensional intra-pulse features and inter-pulse temporal correlations of signals from the same emitter, enabling simultaneous modulation classification, pulse-parameter estimation, and emitter attribution. This framework extends interference recognition from isolated pulses to entire frames, while simultaneously imposing modulation-aware constraints on the signal sorting process. Furthermore, a statistically consistent contrastive objective is designed to enhance intra-emitter compactness and inter-emitter separability, while a geometric consistency constraint improves the robustness of pulse localization. The unified architecture compresses the conventional serial processing chain and eliminates the need for task-dependent input adjustments. Extensive experiments on both simulated and GaoFen-3 (GF-3) satellite data demonstrate the superior performance of the proposed method under dense interference conditions. The code and datasets are publicly available at: https://github.com/QianyueXue/Uni-RSNet.
- 19 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. PP (19391404) , 1-22
Open AccessUni-RSNet: A Unified Recognition-Sorting Framework for SAR Interference Signals in Complex Electromagnetic Environments
Synthetic aperture radar (SAR) often receives interference from multiple emitters operating within the same frequency band. These interference signals are densely overlapped in time and frequency domains and strongly coupled with SAR echoes, which substantially increases the difficulty of signal recognition and sorting. In conventional processing chains, recognition and sorting are treated as independent modules with task-specific inputs, resulting in severe information fragmentation and cumulative-error propagation under dense interference conditions. To address these limitations, this paper proposes a unified recognition-sorting network for overlapping SAR interference signals, termed Uni-RSNet. Based on continuous multi-frame time-frequency representations, Uni-RSNet jointly captures high-dimensional intra-pulse features and inter-pulse temporal correlations of signals from the same emitter, enabling simultaneous modulation classification, pulse-parameter estimation, and emitter attribution. This framework extends interference recognition from isolated pulses to entire frames, while simultaneously imposing modulation-aware constraints on the signal sorting process. Furthermore, a statistically consistent contrastive objective is designed to enhance intra-emitter compactness and inter-emitter separability, while a geometric consistency constraint improves the robustness of pulse localization. The unified architecture compresses the conventional serial processing chain and eliminates the need for task-dependent input adjustments. Extensive experiments on both simulated and GaoFen-3 (GF-3) satellite data demonstrate the superior performance of the proposed method under dense interference conditions. The code and datasets are publicly available at: https://github.com/QianyueXue/Uni-RSNet.
- 27 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Multiscale Residual Alignment Transformer for Remote Sensing Image Change Detection
Deep learning (DL) methods have shown great potential for remote sensing image change detection recently, but still suffer from several limitations. Within the identical semantic concept, significant but irrelevant changes in surface texture, color and spatial shifting of building objects resulted from variations in imaging physical factors, causes feature inconsistency of building objects in bitemporal sences. Conventional DL methods lack the capability to effectively distinguish real changes from irrelevant changes, leading to some false detections. This letter propose a novel framework, the multi-scale residual alignment transformer (AlignFormer), to mitigate the above issues. Specifically, inspired by deformable attention mechanism, we firstly design an adaptive feature alignment module (AFAM) to suppress the inconsistency of feature pairs, where the regions of building can be adaptively focused on and the spatial-temporal dependencies of relevant building objects in feature pairs effectively captured, via scheme of flexibly sampling Keys/Values for each given Query. Besides, we utilize an extremely tiny Swin Transformer as the backbone of differencing-based framework for obtaining hierarchical features. Moreover, inspired by residual learning strategy, three AFAMs are integrated into the framework to form the multi-scale residual architecture for the coarse-to-fine alignment of the paired features. Experimental results confirm the superiority of our proposed method over several state-of-the-art algorithms. Our code will be released at https://github.com/lilei-aircas/AlignFormer_CD.
- 27 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Multiscale Residual Alignment Transformer for Remote Sensing Image Change Detection
Deep learning (DL) methods have shown great potential for remote sensing image change detection recently, but still suffer from several limitations. Within the identical semantic concept, significant but irrelevant changes in surface texture, color and spatial shifting of building objects resulted from variations in imaging physical factors, causes feature inconsistency of building objects in bitemporal sences. Conventional DL methods lack the capability to effectively distinguish real changes from irrelevant changes, leading to some false detections. This letter propose a novel framework, the multi-scale residual alignment transformer (AlignFormer), to mitigate the above issues. Specifically, inspired by deformable attention mechanism, we firstly design an adaptive feature alignment module (AFAM) to suppress the inconsistency of feature pairs, where the regions of building can be adaptively focused on and the spatial-temporal dependencies of relevant building objects in feature pairs effectively captured, via scheme of flexibly sampling Keys/Values for each given Query. Besides, we utilize an extremely tiny Swin Transformer as the backbone of differencing-based framework for obtaining hierarchical features. Moreover, inspired by residual learning strategy, three AFAMs are integrated into the framework to form the multi-scale residual architecture for the coarse-to-fine alignment of the paired features. Experimental results confirm the superiority of our proposed method over several state-of-the-art algorithms. Our code will be released at https://github.com/lilei-aircas/AlignFormer_CD.
- Open Access
- 20 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 5582-5599
EHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
Deep learning (DL)-based methods have shown great potential in the satellite video target tracking community. Nevertheless, most of the methods are still plagued by poor localization capabilities and background interference problems. In this paper, we propose EHTracker, a Siamese-based tracker based on enhanced head network, specifically for tiny targets in satellite videos. EHTracker enhances the localization capability for tiny objects through the proposed enhanced head network, while the proposed background suppression module (BSM) improves the network's ability to suppress background interference. Specifically, to alleviate the problem of overlapping between the foreground and background in the classification branch, we propose a multi-head graph attention refinement module (MGARM). Second, to enable the regression branch to determine the location of feature-poor small targets more accurately, we introduce a gradual regression strategy (GRS). MGARM and GRS together constitute the enhanced head network component of EHTracker. Further, in order to work with the enhanced head network to achieve classification and localization of small targets that lack distinctive features, we design a background suppression module. Extensive experiments are implemented on the SatSOT dataset and SV248S dataset, and the experimental results show that our method achieves state-of-the-art tracking performance.
- 20 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 5582-5599
Open AccessEHTracker: Toward Fine-Grained Localization for Satellite Video Target Tracking
Deep learning (DL)-based methods have shown great potential in the satellite video target tracking community. Nevertheless, most of the methods are still plagued by poor localization capabilities and background interference problems. In this paper, we propose EHTracker, a Siamese-based tracker based on enhanced head network, specifically for tiny targets in satellite videos. EHTracker enhances the localization capability for tiny objects through the proposed enhanced head network, while the proposed background suppression module (BSM) improves the network's ability to suppress background interference. Specifically, to alleviate the problem of overlapping between the foreground and background in the classification branch, we propose a multi-head graph attention refinement module (MGARM). Second, to enable the regression branch to determine the location of feature-poor small targets more accurately, we introduce a gradual regression strategy (GRS). MGARM and GRS together constitute the enhanced head network component of EHTracker. Further, in order to work with the enhanced head network to achieve classification and localization of small targets that lack distinctive features, we design a background suppression module. Extensive experiments are implemented on the SatSOT dataset and SV248S dataset, and the experimental results show that our method achieves state-of-the-art tracking performance.