Automatic discovery of discriminative parts as a quadratic assignment problem - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Automatic discovery of discriminative parts as a quadratic assignment problem

Résumé

Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. We propose to cast the training of parts as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes.
Fichier principal
Vignette du fichier
ICCV17W_quadraParts.pdf (1.81 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01623148 , version 1 (25-10-2017)

Identifiants

  • HAL Id : hal-01623148 , version 1

Citer

Ronan Sicre, Julien Rabin, Yannis Avrithis, Teddy Furon, Frédéric Jurie, et al.. Automatic discovery of discriminative parts as a quadratic assignment problem. ICCV Workshops -- CEFRL, Oct 2017, Venise, Italy. pp.1059-1068. ⟨hal-01623148⟩
456 Consultations
184 Téléchargements

Partager

Gmail Facebook X LinkedIn More