[TGRS 2024]The code in this toolbox implements the proposed network CLOLN in "Channel-Layer-Oriented Lightweight Spectral-Spatial Network for Hyperspectral Image Classification".
and the other two compared methods called Res-LS2CM and Ghostnet in "A lightweight spectral-spatial convolution module for hyperspectral image classification" and "Ghostnet for hyperspectral image classification", respectively. Parts of the code derive from HUAWEI Noah's Ark Lab
Please kindly cite the paper and star this repository if these codes are useful and helpful for your research.
C. Li, B. Rasti, X. Tang, P. Duan, J. Li and Y. Peng, "Channel-Layer-Oriented Lightweight Spectral-Spatial Network for Hyperspectral Image Classification," in IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2024.3350055.
@ARTICLE{Li_CLOLN,
author={Li, Chunchao and Rasti, Behnood and Tang, Xuebin and Duan, Puhong and Li, Jun and Peng, Yuanxi},
journal={IEEE Transactions on Geoscience and Remote Sensing},
title={Channel-Layer-Oriented Lightweight Spectral-Spatial Network for Hyperspectral Image Classification},
year={2024},
volume={},
number={},
pages={1-1},
doi={10.1109/TGRS.2024.3350055}}
It's straightforward to run these codes.
- Make a folder called "Datasets" in the root and put your test datasets in the folder.
- Run the interested corresponding jupyter notebooks.
The suitable main software kits are torch 1.8.0; torchvision 0.9.0;
Chunchao Li : lcc@nudt.edu.cn OR leeachun96@gmail.com