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
EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detection
CV and Pattern Recognition
Finds changes in pictures better, missing less.
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.
Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification
CV and Pattern Recognition
Helps computers identify land from different pictures.