Zongyu Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zongyu Yang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Haitao Li
Chinese academy of surveying and mapping, Beijing, China
1 shared publication- Haiyan Gu
Chinese academy of surveying and mapping, Beijing, China
1 shared publication Haozhu Kong
Chinese academy of surveying and mapping, Beijing, China
1 shared publication- Shaopeng Ding
College of Geodesy and Geomatics, Shandong University of Science and Technology, Qingdao, China
1 shared publication - Yi Yang
Chinese academy of surveying and mapping, Beijing, China
1 shared publication
Latest Publications
- 29 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 5624422
KGDNet: Knowledge-Guided Decoupled Modeling of Heterogeneous Change Mechanisms for Remote Sensing Change Detection
High-resolution remote sensing change detection methods typically rely on single-modal image features, making them highly susceptible to pseudo-changes induced by factors like illumination, shadows, and seasonal variations. Moreover, most approaches adopt a unified binary change paradigm, overlooking the heterogeneous mechanisms of change, such as appearance and disappearance. To address these limitations, this paper presents KGDNet, a knowledge-guided tri-branch network designed for decoupled modeling of heterogeneous change mechanisms in change detection (CD). KGDNet leverages annotation-free monocular depth maps as geometric priors and, through the Guided Alignment and Fusion Module (GAFM), upgrades 2D features to 3D geometry-aware representations. This enhances the discrimination of genuine land-cover changes while effectively suppressing pseudo-changes at the source. The network explicitly decouples three core mechanisms—appearance, difference, and disappearance—using specialized parallel branches to capture distinct change patterns. Additionally, the difference branch dynamically corrects and refines prior knowledge, mitigating contamination from low-quality depth cues. To efficiently process high-resolution imagery, we further propose a Multi-Head Latent Spatiotemporal Attention (MH-LSTA) module that compresses and remaps features in a latent space, substantially reducing computational and memory costs while enhancing the modeling of global spatiotemporal relations. This yields a favorable trade-off between accuracy and efficiency. Comprehensive experiments on public benchmarks demonstrate that KGDNet outperforms representative state-of-the-art (SOTA) methods in key metrics, delivering superior detection accuracy and robustness. This study proposes a knowledge-guided decoupled modeling paradigm that integrates prior knowledge with heterogeneous change mechanisms to enhance the interpretability of change representations. The code and data will be released upon publication at https://github.com/yangzy1217/KGDNet.
- 29 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64 (01962892) , 5624422
KGDNet: Knowledge-Guided Decoupled Modeling of Heterogeneous Change Mechanisms for Remote Sensing Change Detection
High-resolution remote sensing change detection methods typically rely on single-modal image features, making them highly susceptible to pseudo-changes induced by factors like illumination, shadows, and seasonal variations. Moreover, most approaches adopt a unified binary change paradigm, overlooking the heterogeneous mechanisms of change, such as appearance and disappearance. To address these limitations, this paper presents KGDNet, a knowledge-guided tri-branch network designed for decoupled modeling of heterogeneous change mechanisms in change detection (CD). KGDNet leverages annotation-free monocular depth maps as geometric priors and, through the Guided Alignment and Fusion Module (GAFM), upgrades 2D features to 3D geometry-aware representations. This enhances the discrimination of genuine land-cover changes while effectively suppressing pseudo-changes at the source. The network explicitly decouples three core mechanisms—appearance, difference, and disappearance—using specialized parallel branches to capture distinct change patterns. Additionally, the difference branch dynamically corrects and refines prior knowledge, mitigating contamination from low-quality depth cues. To efficiently process high-resolution imagery, we further propose a Multi-Head Latent Spatiotemporal Attention (MH-LSTA) module that compresses and remaps features in a latent space, substantially reducing computational and memory costs while enhancing the modeling of global spatiotemporal relations. This yields a favorable trade-off between accuracy and efficiency. Comprehensive experiments on public benchmarks demonstrate that KGDNet outperforms representative state-of-the-art (SOTA) methods in key metrics, delivering superior detection accuracy and robustness. This study proposes a knowledge-guided decoupled modeling paradigm that integrates prior knowledge with heterogeneous change mechanisms to enhance the interpretability of change representations. The code and data will be released upon publication at https://github.com/yangzy1217/KGDNet.