A Minimalist Approach for Domain Adaptation with Optimal Transport
Abstract
We reveal an intriguing connection between adversarial attacks and cycle monotone maps, also known as optimal transport maps. Based on this finding, we developed a novel method named \textit{source fiction} for semi-supervised optimal transport-based domain adaptation. We conduct experiments on various datasets and show that our method can notably improve the performance of the optimal transport solvers in domain adaptation.
Cite
Text
Asadulaev et al. "A Minimalist Approach for Domain Adaptation with Optimal Transport." Proceedings of The 2nd Conference on Lifelong Learning Agents, 2023.Markdown
[Asadulaev et al. "A Minimalist Approach for Domain Adaptation with Optimal Transport." Proceedings of The 2nd Conference on Lifelong Learning Agents, 2023.](https://mlanthology.org/collas/2023/asadulaev2023collas-minimalist/)BibTeX
@inproceedings{asadulaev2023collas-minimalist,
title = {{A Minimalist Approach for Domain Adaptation with Optimal Transport}},
author = {Asadulaev, Arip and Shutov, Vitaly and Korotin, Alexander and Panfilov, Alexander and Kontsevaya, Vladislava and Filchenkov, Andrey},
booktitle = {Proceedings of The 2nd Conference on Lifelong Learning Agents},
year = {2023},
pages = {1009-1024},
volume = {232},
url = {https://mlanthology.org/collas/2023/asadulaev2023collas-minimalist/}
}