HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Chengxi, Su, Xiaoyu, Wei, Zhiqiang, Hu, Meiqi, Xu, Yichu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916699697053696
author Han, Chengxi
Su, Xiaoyu
Wei, Zhiqiang
Hu, Meiqi
Xu, Yichu
author_facet Han, Chengxi
Su, Xiaoyu
Wei, Zhiqiang
Hu, Meiqi
Xu, Yichu
contents The remote sensing image change detection task is an essential method for large-scale monitoring. We propose HSANet, a network that uses hierarchical convolution to extract multi-scale features. It incorporates hybrid self-attention and cross-attention mechanisms to learn and fuse global and cross-scale information. This enables HSANet to capture global context at different scales and integrate cross-scale features, refining edge details and improving detection performance. We will also open-source our model code: https://github.com/ChengxiHAN/HSANet.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15170
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection
Han, Chengxi
Su, Xiaoyu
Wei, Zhiqiang
Hu, Meiqi
Xu, Yichu
Computer Vision and Pattern Recognition
The remote sensing image change detection task is an essential method for large-scale monitoring. We propose HSANet, a network that uses hierarchical convolution to extract multi-scale features. It incorporates hybrid self-attention and cross-attention mechanisms to learn and fuse global and cross-scale information. This enables HSANet to capture global context at different scales and integrate cross-scale features, refining edge details and improving detection performance. We will also open-source our model code: https://github.com/ChengxiHAN/HSANet.
title HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.15170