HSANET: A Hybrid Self-Cross Attention Network For Remote Sensing Change Detection
By: Chengxi Han , Xiaoyu Su , Zhiqiang Wei and more
Potential Business Impact:
Finds changes in satellite pictures better.
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.
Similar Papers
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
CV and Pattern Recognition
Cleans up blurry X-ray pictures for better health checks.
HSACNet: Hierarchical Scale-Aware Consistency Regularized Semi-Supervised Change Detection
CV and Pattern Recognition
Finds changes in pictures, even with messy data.
Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoising
CV and Pattern Recognition
Cleans up blurry medical scans for better health checks.