Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Yichun, Lan, Yuqing, Xing, Zhihuan, Yang, Xiaoyi, Tang, Tingyue, Yu, Dan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.17665
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913855375933440
author Yu, Yichun
Lan, Yuqing
Xing, Zhihuan
Yang, Xiaoyi
Tang, Tingyue
Yu, Dan
author_facet Yu, Yichun
Lan, Yuqing
Xing, Zhihuan
Yang, Xiaoyi
Tang, Tingyue
Yu, Dan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17665
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy
Yu, Yichun
Lan, Yuqing
Xing, Zhihuan
Yang, Xiaoyi
Tang, Tingyue
Yu, Dan
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title EMRA-proxy: Enhancing Multi-Class Region Semantic Segmentation in Remote Sensing Images with Attention Proxy
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.17665