Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue International Journal of Computer Vision Année : 2016

Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation

Résumé

This paper proposes a novel approach to learning mid-level image models for image categorization and cosegmentation. We represent each image class by a dictionary of discriminative part detectors that best discriminate that class from the background. We learn category-specific part detectors in a weakly supervised setting in which the training images are only labeled with category labels without part / object location labels. We use a latent SVM model regularized by l1,2 group sparsity to learn the discriminative part detectors. Starting from a large set of initial parts, the group sparsity regularizer forces the model to jointly select and optimize a set of discriminative part detectors in a max-margin framework. We propose a stochastic version of a proximal algorithm to solve the corresponding optimization problem. We apply the learned part detectors to image classification and cosegmentation, and quantitative experiments with standard benchmarks show that our approach matches or improves upon the state of the art.
Fichier principal
Vignette du fichier
bare_jrnl_compsoc_arxiv2.pdf (4.26 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01064637 , version 1 (16-09-2014)

Identifiants

Citer

Jian Sun, Jean Ponce. Learning Dictionary of Discriminative Part Detectors for Image Categorization and Cosegmentation. International Journal of Computer Vision, 2016, ⟨10.1007/s11263-016-0899-0⟩. ⟨hal-01064637⟩
295 Consultations
473 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More