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
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, 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.
Complete list of metadatas

Cited literature [56 references]  Display  Hide  Download

https://hal.inria.fr/hal-01110036
Contributor : Minsu Cho <>
Submitted on : Monday, May 4, 2015 - 5:36:22 PM
Last modification on : Thursday, February 7, 2019 - 3:49:57 PM
Long-term archiving on : Wednesday, April 19, 2017 - 3:22:45 PM

File

cho2015.pdf
Files produced by the author(s)

Identifiers

Collections

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 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2015, Boston, United States. pp.1201-1210, ⟨10.1109/CVPR.2015.7298724⟩. ⟨hal-01110036v3⟩

Share

Metrics

Record views

1094

Files downloads

851