Unsupervised Object Discovery for Instance Recognition

Abstract : Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discrim-inative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects.
Type de document :
Communication dans un congrès
WACV 2018 - IEEE Winter Conference on Applications of Computer Vision, Mar 2018, Lake Tahoe, United States. IEEE, pp.1-10, 〈10.1109/WACV.2018.00194〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01842143
Contributeur : Yannis Avrithis <>
Soumis le : mercredi 18 juillet 2018 - 00:46:58
Dernière modification le : vendredi 7 septembre 2018 - 15:48:05
Document(s) archivé(s) le : vendredi 19 octobre 2018 - 16:07:43

Fichier

C105.wacv18.disco.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum. Unsupervised Object Discovery for Instance Recognition. WACV 2018 - IEEE Winter Conference on Applications of Computer Vision, Mar 2018, Lake Tahoe, United States. IEEE, pp.1-10, 〈10.1109/WACV.2018.00194〉. 〈hal-01842143〉

Partager

Métriques

Consultations de la notice

95

Téléchargements de fichiers

27