Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals

Minsu Cho 1, 2 Suha Kwak 1, 2 Cordelia Schmid 3 Jean Ponce 1, 2
1 LIENS - Laboratoire d'informatique de l'école normale supérieure
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any assumption of a single dominant class. This is far more general than typical colocalization, cosegmentation, or weakly-supervised localization tasks. We tackle the discovery and localization problem using a part-based region matching approach: We use off-the-shelf region proposals to form a set of candidate bounding boxes for objects and object parts. These regions are efficiently matched across images using a probabilistic Hough transform that evaluates the confidence for each candidate correspondence considering both appearance and spatial consistency. Dominant objects are discovered and localized by comparing the scores of candidate regions and selecting those that stand out over other regions containing them. Extensive experimental evaluations on standard benchmarks demonstrate that the proposed approach significantly outperforms the current state of the art in colocalization, and achieves robust object discovery in challenging mixed-class datasets.
Type de document :
Communication dans un congrès
CVPR 2015 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. IEEE, Proceedings IEEE Conference on Computer Vision & Pattern Recognition, pp.1201-1210, <10.1109/CVPR.2015.7298724>
Liste complète des métadonnées

https://hal.inria.fr/hal-01110036
Contributeur : Minsu Cho <>
Soumis le : lundi 4 mai 2015 - 17:36:22
Dernière modification le : jeudi 9 février 2017 - 11:45:10

Fichier

cho2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UGA | LJK_GI | LJK | LJK_GI_LEAR | INRIA | PSL

Citation

Minsu Cho, Suha Kwak, Cordelia Schmid, Jean Ponce. Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals. CVPR 2015 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. IEEE, Proceedings IEEE Conference on Computer Vision & Pattern Recognition, pp.1201-1210, <10.1109/CVPR.2015.7298724>. <hal-01110036v3>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

675

Téléchargements du document

589

Contact


archive-ouverte@inria.fr