Skip to Main content Skip to Navigation
Conference papers

Unsupervised Joint Object Discovery and Segmentation in Internet Images

Michael Rubinstein 1, 2 Armand Joulin 2, 3 Johannes Kopf 2 Ce Liu 2 
3 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : Suha Kwak Connect in order to contact the contributor
Submitted on : Monday, September 15, 2014 - 6:35:44 PM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Tuesday, December 16, 2014 - 11:41:35 AM


Files produced by the author(s)




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. pp.1939-1946, ⟨10.1109/CVPR.2013.253⟩. ⟨hal-01064227⟩



Record views


Files downloads