Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion

Code for the paper: "Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion", JSTARS 2023. [paper]
State-of-the-art (SOTA) performance of remote sensing image fusion.

Method

RSAM

We propose a novel recursive self-attention module (RSAM), which consists of two stages: spatial-spectral similarity extraction and self-attention weight generation. The proposed RSAM employs a global-to-local strategy to capture the global interdependencies of two distinct local locations in the feature map. This method allows for simultaneous consideration of both spatial and spectral information while focusing on more mutual information between spectral and spatial dimensions.

Code

see ./model/RSAM.py

Citation

@ARTICLE{10294268,
  author={Liu, Chuang and Wei, Lu and Zhang, Zhiqi and Feng, Xiaoxiao and Xiang, Shao},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion}, 
  year={2023},
  volume={16},
  number={},
  pages={10067-10083},
  doi={10.1109/JSTARS.2023.3327167}}

JUSTM0VE0N/RSANet