The implementation for Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation.

The code for this project is based on the Pytorch implementation of StyleGAN2+ADA. Thanks a lot for their work. Please first read the instructions provided for StyleGAN2+ADA. We mainly modify training/loss.py and training/networks.py. The instructions are the same as StyleGAN2-ada-pytorch.

If you find this work useful, please cite our paper as:

@misc{su2024intriguing,
      title={Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation}, 
      author={Xingzhe Su and Wenwen Qiang and Jie Hu and Fengge Wu and Changwen Zheng and Fuchun Sun},
      year={2024},
      eprint={2303.05240},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}