Code release for "Conditional Adversarial Domain Adaptation" (NIPS 2018)

New version: https://github.com/thuml/Transfer-Learning-Library

Processed SVHN_dataset is here. We change the original mat into images. Other transformed images are in data/svhn2mnist and data/usps2mnist. Dataset_train.txt are lists for source and target domains and Dataset_test.txt are lists for test.

Office-31 dataset can be found here.

Office-Home dataset can be found here.

VisDA 2017 dataset can be found here in the classification track.

We release the Image-clef dataset we used here.

Training instructions for Caffe and PyTorch are in the README.md in caffe and pytorch respectively.

Tensorflow version is under developing.

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

@inproceedings{long2018conditional,
  title={Conditional adversarial domain adaptation},
  author={Long, Mingsheng and Cao, Zhangjie and Wang, Jianmin and Jordan, Michael I},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1645--1655},
  year={2018}
}

If you have any problem about our code, feel free to contact

• caozj@cs.stanford.edu
• youkaichao@gmail.com
• shuyang5656@gmail.com
• longmingsheng@gmail.com

or describe your problem in Issues.