Vicente, S; Kolmogorov, V; Rother, C; (2010) Cosegmentation Revisited: Models and Optimization. In: Daniilidis, K and Maragos, P and Paragios, N, (eds.) UNSPECIFIED (465 - 479). SPRINGER-VERLAG BERLIN
Full text not available from this repository.
The problem of cosegmentation consists of segmenting the same object (or objects of the same class) in two or more distinct images. Recently a number of different models have been proposed for this problem. However, no comparison of such models and corresponding optimization techniques has been done so far. We analyze three existing models: the L1 norm model of Bother et al. , the L2 norm model of Mukherjee et al.  and the "reward" model of Hochbaum and Singh . We also study a new model, which is a straightforward extension of the Boykov-Jolly model for single image segmentation .In terms of optimization, we use a Dual Decomposition (DD) technique in addition to optimization methods in [1,2]. Experiments show a significant improvement of DD over published methods. Our main conclusion, however, is that the new model is the best overall because it: (i) has fewest parameters; (ii) is most robust in practice, and (iii) can be optimized well with an efficient EM-style procedure.
|Title:||Cosegmentation Revisited: Models and Optimization|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only: edit this record