Co-segmentation by Composition
Authors:
- Alon FaktorAFAlon Faktor
- Michal IraniMIMichal Irani
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1297-1304
Abstract
Given a set of images which share an object from the same semantic category, we would like to co-segment the shared object. We define 'good' co-segments to be ones which can be easily composed (like a puzzle) from large pieces of other co-segments, yet are difficult to compose from remaining image parts. These pieces must not only match well but also be statistically significant (hard to compose at random). This gives rise to co-segmentation of objects in very challenging scenarios with large variations in appearance, shape and large amounts of clutter. We further show how multiple images can collaborate and "score" each others' co-segments to improve the overall fidelity and accuracy of the co-segmentation. Our co-segmentation can be applied both to large image collections, as well as to very few images (where there is too little data for unsupervised learning). At the extreme, it can be applied even to a single image, to extract its co-occurring objects. Our approach obtains state-of-the-art results on benchmark datasets. We further show very encouraging co-segmentation results on the challenging PASCAL-VOC dataset.Keywords
This publication has 11 references indexed in Scilit:
- Unsupervised Joint Object Discovery and Segmentation in Internet Images2013
- Unsupervised co-segmentation through region matching2012
- A hierarchical image clustering cosegmentation framework2012
- Object cosegmentation2011
- Discriminative clustering for image co-segmentation2010
- iCoseg: Interactive co-segmentation with intelligent scribble guidance2010
- PatchMatch2009
- In defense of Nearest-Neighbor based image classification2008
- Using Multiple Segmentations to Discover Objects and their Extent in Image Collections2006
- LOCUS: learning object classes with unsupervised segmentation2005