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

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:this https URL.

@article{han2025_2504.15170,
  title={ HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection },
  author={ Chengxi Han and Xiaoyu Su and Zhiqiang Wei and Meiqi Hu and Yichu Xu },
  journal={arXiv preprint arXiv:2504.15170},
  year={ 2025 }
}