Skip to Main content Skip to Navigation
Journal articles

Optimal Transport for Domain Adaptation

Abstract : Domain adaptation is one of the most chal- lenging tasks of modern data analytics. If the adapta- tion is done correctly, models built on a specific data representation become more robust when confronted to data depicting the same classes, but described by another observation system. Among the many strategies proposed, finding domain-invariant representations has shown excel- lent properties, in particular since it allows to train a unique classifier effective in all domains. In this paper, we propose a regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains. We learn a transportation plan matching both PDFs, which constrains labeled samples of the same class in the source domain to remain close during transport. This way, we exploit at the same time the labeled samples in the source and the distributions observed in both domains. Experiments on toy and challenging real visual adaptation examples show the interest of the method, that consistently outperforms state of the art approaches. In addition, numerical experiments show that our approach leads to better performances on domain invariant deep learning features and can be easily adapted to the semi- supervised case where few labeled samples are available in the target domain.
Complete list of metadata

Cited literature [51 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01377220
Contributor : Nicolas Courty Connect in order to contact the contributor
Submitted on : Thursday, October 6, 2016 - 3:17:10 PM
Last modification on : Wednesday, November 3, 2021 - 5:14:55 AM
Long-term archiving on: : Friday, February 3, 2017 - 4:19:10 PM

File

OTPAMI.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Courty, Rémi Flamary, Devis Tuia, Alain Rakotomamonjy. Optimal Transport for Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 39 (9), pp.1853-1865. ⟨10.1109/tpami.2016.2615921⟩. ⟨hal-01377220⟩

Share

Metrics

Record views

1115

Files downloads

1992