EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy

High-resolution remote sensing (HRRS) image segmentation is challenging due to complex spatial layouts and diverse object appearances. While CNNs excel at capturing local features, they struggle with long-range dependencies, whereas Transformers can model global context but often neglect local details and are computationallythis http URLpropose a novel approach, Region-Aware Proxy Network (RAPNet), which consists of two components: Contextual Region Attention (CRA) and Global Class Refinement (GCR). Unlike traditional methods that rely on grid-based layouts, RAPNet operates at the region level for more flexible segmentation. The CRA module uses a Transformer to capture region-level contextual dependencies, generating a Semantic Region Mask (SRM). The GCR module learns a global class attention map to refine multi-class information, combining the SRM and attention map for accuratethis http URLon three public datasets show that RAPNet outperforms state-of-the-art methods, achieving superior multi-class segmentation accuracy.

@article{yu2025_2505.17665,
  title={ EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy },
  author={ Yichun Yu and Yuqing Lan and Zhihuan Xing and Xiaoyi Yang and Tingyue Tang and Dan Yu },
  journal={arXiv preprint arXiv:2505.17665},
  year={ 2025 }
}