Unsupervised Joint Object Discovery and Segmentation in Internet Images

Michael Rubinstein 1, 2 Armand Joulin 2, 3 Johannes Kopf 2 Ce Liu 2
1 MIT - Massachusetts Institute of Technology
2 Microsoft Research [Redmond]
3 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : We present a new unsupervised algorithm to discover and segment out common objects from large and diverse image collections. In contrast to previous co-segmentation methods, our algorithm performs well even in the presence of significant amounts of noise images (images not containing a common object), as typical for datasets collected from Internet search. The key insight to our algorithm is that common object patterns should be salient within each image, while being sparse with respect to smooth transformations across images. We propose to use dense correspondences between images to capture the sparsity and visual variability of the common object over the entire database, which enables us to ignore noise objects that may be salient within their own images but do not commonly occur in others. We performed extensive numerical evaluation on established co-segmentation datasets, as well as several new datasets generated using Internet search. Our approach is able to effectively segment out the common object for diverse object categories, while naturally identifying images where the common object is not present.
Type de document :
Communication dans un congrès
CVPR 2013 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, Oregon, United States. IEEE, pp.1939-1946, 2013, 〈10.1109/CVPR.2013.253〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01064227
Contributeur : Suha Kwak <>
Soumis le : lundi 15 septembre 2014 - 18:35:44
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : mardi 16 décembre 2014 - 11:41:35

Fichier

ObjectDiscovery-cvpr13.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | ENS-PARIS | PSL | INRIA-ROCQ

Citation

Michael Rubinstein, Armand Joulin, Johannes Kopf, Ce Liu. Unsupervised Joint Object Discovery and Segmentation in Internet Images. CVPR 2013 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, Oregon, United States. IEEE, pp.1939-1946, 2013, 〈10.1109/CVPR.2013.253〉. 〈hal-01064227〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

277

Téléchargements de fichiers

589

Contact


archive-ouverte@inria.fr