Code release for Mahalanobis distance guided conditional adversarial learning for univeral domain adaptation.
If you have any problem about our code, feel free to contact [email protected] or describe your problem in issues.
We reuse some basic code in A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks (https://github.com/pokaxpoka/deep_Mahalanobis_detector) and dalib (https://dalib.readthedocs.io/en/latest/tutorial.html).
We would like to express our sincere gratitude to the authors of deep_Mahalanobis_detector and dalib for their contributions to the domain adaptation community.
All the code about the part declared as novelty in this paper is done by ourselves.