Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

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

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.
Fichier principal
Vignette du fichier
Xu-ICPR-2016.pdf (6.41 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01416419 , version 1 (14-12-2016)

Identifiers

Cite

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. pp.3228-3233, ⟨10.1109/ICPR.2016.7900132⟩. ⟨hal-01416419⟩
342 View
348 Download

Altmetric

Share

Gmail Facebook X LinkedIn More