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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...