During the training phase, process the dataset according to ./dataset and run:

python train.py

During the testing phase, run:

python test.py

Run the ./matlab_code_Make_d/maked.m to generate a precise customized target spectrum for subsequent spectral detection. The corrected spectrum has been experimentally verified to significantly enhance the detection accuracy across various methods.

If you find this project useful for your research, please use the following BibTeX entry.

@article{lei2023semantic,
  title={A Semantic Transferred Priori for Hyperspectral Target Detection With Spatial--Spectral Association},
  author={Lei, Jie and Xu, Simin and Xie, Weiying and Zhang, Jiaqing and Li, Yunsong and Du, Qian},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  volume={61},
  pages={1--14},
  year={2023},
  publisher={IEEE}
}