/MixupDA

[ICML22] Balancing Discriminability and Transferability for Source-Free Domain Adaptation

Primary LanguagePython

Balancing Discriminability and Transferability for Source-Free DA (ICML22)

Code for our ICML 2022 paper 'Balancing Discriminability and Transferability for Source-Free Domain Adaptation'.

[Paper] [Project Page]

Extra results

  • CosDA provides results on Continual Source-Free DA with our proposed edge-mixup. Many thanks to them.

Citation

If you find our work useful in your research, please cite the following paper:

@InProceedings{pmlr-v162-kundu22a,
  title = 	 {Balancing Discriminability and Transferability for Source-Free Domain Adaptation},
  author =       {Kundu, Jogendra Nath and Kulkarni, Akshay R and Bhambri, Suvaansh and Mehta, Deepesh and Kulkarni, Shreyas Anand and Jampani, Varun and Radhakrishnan, Venkatesh Babu},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {11710--11728},
  year = 	 {2022},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  publisher =    {PMLR},
}