Multi-Paced Dictionary Learning for Cross-Domain Retrieval and RecognitionReportar como inadecuado

Multi-Paced Dictionary Learning for Cross-Domain Retrieval and Recognition - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

1 University of Trento Trento 2 PERCEPTION - Interpretation and Modelling of Images and Videos Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble 3 FBK - Fondazione Bruno Kessler Trento, Italy

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.

Autor: Dan Xu - Jingkuan Song - Xavier Alameda-Pineda - Elisa Ricci - Nicu Sebe -



Documentos relacionados