EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy
Year: 2025
Type: preprint
Abstract: 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 computationally expensive.We propose 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 accurate segmentation.Experiments on three public datasets show that RAPNet outperforms state-of-the-art methods, achieving superior multi-class segmentation accuracy.
Source: arXiv (Cornell University)
Authors: Yu, Yichun, Lan, Yuqing, Xing, Zhihuan, Yang, Xiaoyi, Tang, Tingyue, Yu, Dan
Institution: Beihang University
Language: English
Subfield: Media Technology
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6967215401
Cites:
Cited by:
Related to: