DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation

Abstract : In computer vision, one is often confronted with problems of domain shifts, which occur when one applies a classifier trained on a source dataset to target data sharing similar characteristics (e.g. same classes), but also different latent data structures (e.g. different acquisition conditions). In such a situation, the model will perform poorly on the new data, since the classifier is specialized to recognize visual cues specific to the source domain. In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier. We applied DeepJDOT to a series of visual recognition tasks, where it compares favorably against state-of-the-art deep domain adaptation methods.
Type de document :
Communication dans un congrès
ECCV 2018 - 15th European Conference on Computer Vision, Sep 2018, Munich, Germany. Springer, 11208, pp.467-483, LNCS. 〈10.1007/978-3-030-01225-0_28〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01956356
Contributeur : Nicolas Courty <>
Soumis le : samedi 15 décembre 2018 - 15:32:40
Dernière modification le : mardi 15 janvier 2019 - 13:30:17

Lien texte intégral

Identifiants

Citation

Bharath Bhushan Damodaran, Benjamin Kellenberger, Remi Flamary, Devis Tuia, Nicolas Courty. DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation. ECCV 2018 - 15th European Conference on Computer Vision, Sep 2018, Munich, Germany. Springer, 11208, pp.467-483, LNCS. 〈10.1007/978-3-030-01225-0_28〉. 〈hal-01956356〉

Partager

Métriques

Consultations de la notice

76