HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection
This work addresses large-scale monitoring in remote sensing, but it appears incremental as it builds on existing attention-based methods for change detection.
The paper tackles remote sensing image change detection by proposing HSANet, a network that uses hierarchical convolution and hybrid self-cross attention mechanisms to capture global context and fuse cross-scale features, resulting in improved detection performance with refined edge details.
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.