Awesome

Calibrator-Domain-Adaptation

Release code for light-weight calibrator: a separable component for unsupervised domain adaptation

use train_cls.py to reproduce our results on digits

Our best results are obtained if we used synthetic data produced by CycleGAN as source domain. Will add that too.

Feel free to cite us if you find this useful to your research

@inproceedings{ye2020light,
  title={Light-weight calibrator: a separable component for unsupervised domain adaptation},
  author={Ye, Shaokai and Wu, Kailu and Zhou, Mu and Yang, Yunfei and Tan, Sia Huat and Xu, Kaidi and Song, Jiebo and Bao, Chenglong and Ma, Kaisheng},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={13736--13745},
  year={2020}
}
{"mode":"full","isActive":false}