This is a PyTorch implementation of the IJCNN 2019 paper.

1. We present TCP as a unified approach for accelerating deep unsupervised domain adaptation models. TCP is a generic, accurate, and efficient compression method that can be easily implemented by most deep learning libraries.
2. TCP is able to reduce negative transfer by considering the cross-domain distribution discrepancy using the proposed Transfer Channel Evaluation module.
3. Extensive experiments on two public UDA datasets demonstrate the significant superiority of TCP.

If you use this code for your research, please consider citing:

@inproceedings{yu2019accelerating,
  title={Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning},
  author={Yu, Chaohui and Wang, Jindong and Chen, Yiqiang and Wu, Zijing},
  booktitle={The IEEE International Joint Conference on Neural Networks (IJCNN)},
  year={2019}
}