NAPG: Neighborhood-Assisted Multiprototype Group Model for Cross-Domain Semantic Segmentation of Remote Sensing Images
- 21 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-19
Abstract
Unsupervised domain adaptation (UDA) is crucial for semantic segmentation of remote sensing images (RS-SS), particularly when data distributions differ between source and target domains. Existing prototype-based UDA methods struggle with complex land cover class distributions and spatial information capture. To address these limitations, the Neighborhood-Assisted Multi-Prototype Group (NAPG) model is proposed. This model enhances cross-domain adaptability and spatial context richness by dynamically determining the number of prototype features and integrating neighborhood similarity gradients. Specifically, NAPG employs the Cross-Domain Representation of Multi-Prototype Group (CDR-MPG) module to generate multi-prototype group, capturing land cover complexity more effectively. Additionally, the Gradient Neighborhood Consistency Estimation (GNCE) module improves spatial representation by reducing intra-class variance and alleviating feature inconsistency. Experiments demonstrate that the proposed NAPG model outperforms state-of-the-art UDA methods across multiple datasets, achieving an mean intersection over union (mIoU) improvement of 3%. The source code is publicly available at https://github.com/Fanrongbo/NAPG-UDA-RS-SS.Keywords
Funding Information
- Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University (CX2023064)
- National Natural Science Foundation of China (12174314)
- National Science Foundation for Young Scientists of China (12404515)
- National Natural Science Foundation of China (62276208)
This publication has 60 references indexed in Scilit:
- Denoising Vision Transformers2024
- Boundary-refined prototype generation: A general end-to-end paradigm for semi-supervised semantic segmentationEngineering Applications of Artificial Intelligence, 2024
- Few-Shot Domain Adaptation via Prompt-Guided Multi-prototype Alignment Network2024
- RescueNet: A High Resolution UAV Semantic Segmentation Dataset for Natural Disaster Damage AssessmentScientific Data, 2023
- An unsupervised domain adaptation approach for change detection and its application to deforestation mapping in tropical biomesISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Learning deep semantic segmentation network under multiple weakly-supervised constraints for cross-domain remote sensing image semantic segmentationISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation2018
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009