gzqhappy/fgda

FGDA

Code for paper "Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation" which has been accept by ICCV2021.

Requirements

• Python 3.5
• torch 1.1.0
• torchvision 0.3.0

Training

train_FGDA_CDANE.py

train_FGDA_MDD.py

Citation

Please cite our paper if you use our code in your research:

@article{zhiqiang2021gradient,
  title={Gradient Distribution Alignment Certificates Better Adversarial Domain Adaptation},
  author={Gao, Zhiqiang and Zhang, Shufei and Huang, Kaizhu and Wang, Qiufeng and Zhong, Chaoliang},
  journal={Proceedings of the IEEE international conference on computer vision (ICCV)},
  year={2021}
}

fgda's Issues

Would you mind provide your 'models.py' file?

Dear authors,
I have read your paper and find your work is interesting and meaningful, thus I want to reproduce your work. But I can not find your 'models.py' file, would you mind provide your 'models.py' file?

请问有论文中画t-sne图的代码吗

Can you please provide sample 'dslr_list.txt' or 'amazon_list.txt' file......