Multi-class cosegmentation

9 years 2 months ago
Multi-class cosegmentation
Bottom-up, fully unsupervised segmentation remains a daunting challenge for computer vision. In the cosegmentation context, on the other hand, the availability of multiple images assumed to contain instances of the same object classes provides a weak form of supervision that can be exploited by discriminative approaches. Unfortunately, most existing algorithms are limited to a very small number of images and/or object classes (typically two of each). This paper proposes a novel energy-minimization approach to cosegmentation that can handle multiple classes and a significantly larger number of images. The proposed cost function combines spectral- and discriminative-clustering terms, and it admits a probabilistic interpretation. It is optimized using an efficient EM method, initialized using a convex quadratic approximation of the energy. Comparative experiments show that the proposed approach matches or improves the state of the art on several standard datasets.
Armand Joulin, Francis Bach, Jean Ponce
Added 28 Sep 2012
Updated 28 Sep 2012
Type Journal
Year 2012
Where CVPR
Authors Armand Joulin, Francis Bach, Jean Ponce
Comments (0)