2013 IEEE Conference on Computer Vision and Pattern Recognition (2010)
San Francisco, CA, USA
June 13, 2010 to June 18, 2010
Jean Ponce , Ecole Normale Supérieure, 45 rue d'Ulm, 75005 Paris, France
Armand Joulin , INRIA, 23 avenue d'Italie, 75214 Paris, France
Francis Bach , INRIA, 23 avenue d'Italie, 75214 Paris, France
Purely bottom-up, unsupervised segmentation of a single image into foreground and background regions remains a challenging task for computer vision. Co-segmentation is the problem of simultaneously dividing multiple images into regions (segments) corresponding to different object classes. In this paper, we combine existing tools for bottom-up image segmentation such as normalized cuts, with kernel methods commonly used in object recognition. These two sets of techniques are used within a discriminative clustering framework: the goal is to assign foreground/background labels jointly to all images, so that a supervised classifier trained with these labels leads to maximal separation of the two classes. In practice, we obtain a combinatorial optimization problem which is relaxed to a continuous convex optimization problem, that can itself be solved efficiently for up to dozens of images. We illustrate the proposed method on images with very similar foreground objects, as well as on more challenging problems with objects with higher intra-class variations.
Jean Ponce, Armand Joulin, Francis Bach, "Discriminative clustering for image co-segmentation", 2013 IEEE Conference on Computer Vision and Pattern Recognition, vol. 00, no. , pp. 1943-1950, 2010, doi:10.1109/CVPR.2010.5539868