Sample Selection for Universal Domain Adaptation
DOI:
https://doi.org/10.1609/aaai.v35i10.17042Keywords:
Transfer/Adaptation/Multi-task/Meta/Automated LearningAbstract
This paper studies the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of the shared classes. The score is used to select samples in the target domain for which to apply specific losses during training; pseudo-labels for high scoring samples and confidence regularization for low scoring samples. Taken together, our method is shown to outperform, by a sizeable margin, the current state of the art on the literature benchmarks.Downloads
Published
2021-05-18
How to Cite
Lifshitz, O., & Wolf, L. (2021). Sample Selection for Universal Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(10), 8592-8600. https://doi.org/10.1609/aaai.v35i10.17042
Issue
Section
AAAI Technical Track on Machine Learning III