Abstract : 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.
Type de document :
Communication dans un congrès
ICCV Workshops -- CEFRL, Oct 2017, Venise, Italy. 2017
https://hal.archives-ouvertes.fr/hal-01623148
Contributeur : Frederic Jurie
<>
Soumis le : mercredi 25 octobre 2017 - 09:51:56
Dernière modification le : mardi 5 juin 2018 - 18:00:02
Document(s) archivé(s) le : vendredi 26 janvier 2018 - 12:39:55
