zwzpower/multiclassda

Code release for "Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice"

MultiClassDA

Code release for "Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice", which is an extension of our preliminary work of SymmNets [Paper] [Code]

Code to be updated:

1. Code of McDalNets
   1. For the Office-31, ImageCLEF, Office-Home, VisDA-2017 datasets (Finished)
   2. For the Digits dataset
2. Code of SymNets-V2
   1. For the Closed Set DA
      1. Based on the ResNet (Finished)
      2. Based on the AlexNet
      3. For the Digits dataset
      4. Strengthened for Closed Set UDA
   2. For the Partial DA
      1. Based on the ResNet (Finished)
      2. Based on the AlexNet
   3. For the Open Set DA
      1. Based on the ResNet (Finished)

Dataset

To be updated.

Citation

@inproceedings{zhang2019domain,
  title={Domain-symmetric networks for adversarial domain adaptation},
  author={Zhang, Yabin and Tang, Hui and Jia, Kui and Tan, Mingkui},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5031--5040},
  year={2019}
}
@article{zhang2020unsupervised,
  title={Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice},
  author={Zhang, Yabin and Deng, Bin and Tang, Hui and Zhang, Lei and Jia, Kui},
  journal={arXiv preprint arXiv:2002.08681},
  year={2020}
}

Contact

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

• [email protected]

or describe your problem in Issues.