Joint Adversarial Network With Semantic and Topology Fusion for Cross-Scene Hyperspectral Image Classification

Implementation of paper:

• Joint Adversarial Network With Semantic and Topology Fusion for Cross-Scene Hyperspectral Image Classification
  IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS), 2024.
  Ronghua Shang, Yuhao Xie, Weitong Zhang, Jie Feng, Songhua Xu

Framwork of JAN-STF. (Details of CGCAN, TADCA and LTCAN can be found in paper.)

Environment

Ubuntu 20.04.2 LTS, python 3.8.10, PyTorch 1.12.1.

Datasets

Application website： Houston, HyRANK, Pavia

(a),(b): False color and GT maps of Houston2013. (c), (d): False color and GT maps of Houston2018.

(a),(b): False color and GT maps of Dioni. (c), (d): False color and GT maps of Loukia.

(a),(b): False color and GT maps of PaviaU. (c), (d): False color and GT maps of PaviaC.

Usage

cd code
python train.py

Citation

If you find our paper or code helpful, please cite our work.

@ARTICLE{10559841,
  author={Shang, Ronghua and Xie, Yuhao and Zhang, Weitong and Feng, Jie and Xu, Songhua},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Joint Adversarial Network With Semantic and Topology Fusion for Cross-Scene Hyperspectral Image Classification}, 
  year={2024},
  volume={62},
  number={},
  pages={1-16},
  doi={10.1109/TGRS.2024.3415965}}

Contributors

For any questions, feel free to open an issue or contact us:

• [email protected]