NAPG: Neighborhood-Assisted Multiprototype Group Model for Cross-Domain Semantic Segmentation of Remote Sensing Images

Unsupervised domain adaptation (UDA) is crucial for conciseness and readability (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 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 multiprototype group (CDR-MPG) module to generate multiprototype group (MPG), capturing land cover complexity more effectively. Additionally, the gradient neighborhood consistency estimation (GNCE) module improves spatial representation by reducing intraclass variance and alleviating feature inconsistency. Experiments demonstrate that the proposed NAPG model outperforms the state-of-the-art UDA methods across multiple datasets, achieving a mean intersection over union (mIoU) improvement of 3%.