Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition

Dan Xu 1 Jingkuan Song 1 Xavier Alameda-Pineda 2, 1 Elisa Ricci 3 Nicu Sebe 1
2 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Several applications benefit from learning coupled representations able to describe data from multiple sources. For instance, cross-domain dictionary learning methods demonstrated to be particularly effective. In this paper we introduce Multi-Paced Dictionary Learning (MPDL) and propose an instan-tiation of it under the framework of cross-domain dictionary learning. MPDL is inspired by previous works on self-paced learning, a framework able to enhance the accuracy of conventional learning models by presenting the training data in a meaningful order, i.e. easy samples are provided first. However, most of existing self-paced learning methods only consider a single modality, while MPDL is specifically designed to assess the learning pace when data from multiple sources are available. We present the model and propose an efficient algorithm to learn the dictionaries and codes. The approach is validated via experiments on two different tasks, namely cross-media retrieval and sketch-to-photo face recognition, using publicly available datasets.
Type de document :
Communication dans un congrès
IEEE International Conference on Pattern Recognition, Dec 2016, Cancun, Mexico. IEEE, pp.3228-3233, 〈10.1109/ICPR.2016.7900132〉
Liste complète des métadonnées

Littérature citée [34 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01416419
Contributeur : Team Perception <>
Soumis le : mercredi 14 décembre 2016 - 14:42:07
Dernière modification le : mercredi 11 avril 2018 - 01:59:07
Document(s) archivé(s) le : mercredi 15 mars 2017 - 13:40:05

Fichier

Xu-ICPR-2016.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Dan Xu, Jingkuan Song, Xavier Alameda-Pineda, Elisa Ricci, Nicu Sebe. Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition. IEEE International Conference on Pattern Recognition, Dec 2016, Cancun, Mexico. IEEE, pp.3228-3233, 〈10.1109/ICPR.2016.7900132〉. 〈hal-01416419〉

Partager

Métriques

Consultations de la notice

411

Téléchargements de fichiers

310