Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning

This is a PyTorch implementation of the IJCNN 2019 paper.

The contributions of this paper are summarized as follows:

  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.

    Citation:

    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} }

```