Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation

Rémi Emonet
Damien Muselet
Marc Sebban

Résumé

Domain adaptation (DA) has gained a lot of success in the recent years in Computer Vision to deal with situations where the learning process has to transfer knowledge from a source domain to a target domain. In this paper, we introduce a novel parameter free unsupervised DA approach based on both subspace alignment and the selection of landmarks similarly distributed between the two domains. Those landmarks are selected so as to reduce the discrepancy between the domains and then to allow a non linearly projection of the data in the same space where an efficient subspace alignment (in closed-form) is performed. We carry out a large experimental comparison in visual domain adaptation that shows that our new method outperforms the most recent DA approaches.
Fichier principal
Vignette du fichier
2015-cvpr.pdf (1.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01124975 , version 1 (18-05-2015)

Identifiants

  • HAL Id : hal-01124975 , version 1

Citer

Rahaf Aljundi, Rémi Emonet, Damien Muselet, Marc Sebban. Landmarks-based Kernelized Subspace Alignment for Unsupervised Domain Adaptation. Computer Vision and Pattern Recognition (CVPR'2015), Jun 2015, Boston, United States. ⟨hal-01124975⟩
331 Consultations
399 Téléchargements

Partager

Gmail Facebook X LinkedIn More