RSANet

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

★ 12 Open GitHub ↗

Code for the paper: "Recursive Self-Attention Modules-Based Network for Panchromatic and Multispectral Image Fusion", JSTARS 2023.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# 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]](https://ieeexplore.ieee.org/document/10294268)
- State-of-the-art (SOTA) performance of remote sensing image fusion.

![RSANet](https://github.com/JUSTM0VE0N/RSANet/blob/main/charts/Fig%201.png#pic_center)

# Method
## RSAM
![RSAM](https://github.com/JUSTM0VE0N/RSANet/blob/main/charts/RSAM.png#pic_center)

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
```shell
@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}}
```

# Contact
### We are glad to hear from you. If you have any questions, please feel free to contact us.

RSANet

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README