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 metadatas

Contributor : Alain Rakotomamonjy <>
Submitted on : Friday, April 26, 2019 - 11:21:55 PM
Last modification on : Sunday, April 28, 2019 - 1:23:11 AM


  • HAL Id : hal-02112786, version 1


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, 2017. ⟨hal-02112786⟩



Record views