Cosegmentation revisited: Models and optimization

S. Vicente, V. Kolmogorov, C. Rother, in:, Springer, 2010, pp. 465–479.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
; ;
Series Title
LNCS
Abstract
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 Rother et al. [1], the L2 norm model of Mukherjee et al. [2] and the "reward" model of Hochbaum and Singh [3]. We also study a new model, which is a straightforward extension of the Boykov-Jolly model for single image segmentation [4]. 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.
Publishing Year
Date Published
2010-08-30
Volume
6312
Page
465 - 479
Conference
ECCV: European Conference on Computer Vision
IST-REx-ID

Cite this

Vicente S, Kolmogorov V, Rother C. Cosegmentation revisited: Models and optimization. In: Vol 6312. Springer; 2010:465-479. doi:10.1007/978-3-642-15552-9_34
Vicente, S., Kolmogorov, V., & Rother, C. (2010). Cosegmentation revisited: Models and optimization (Vol. 6312, pp. 465–479). Presented at the ECCV: European Conference on Computer Vision, Springer. https://doi.org/10.1007/978-3-642-15552-9_34
Vicente, Sara, Vladimir Kolmogorov, and Carsten Rother. “Cosegmentation Revisited: Models and Optimization,” 6312:465–79. Springer, 2010. https://doi.org/10.1007/978-3-642-15552-9_34.
S. Vicente, V. Kolmogorov, and C. Rother, “Cosegmentation revisited: Models and optimization,” presented at the ECCV: European Conference on Computer Vision, 2010, vol. 6312, pp. 465–479.
Vicente S, Kolmogorov V, Rother C. 2010. Cosegmentation revisited: Models and optimization. ECCV: European Conference on Computer Vision, LNCS, vol. 6312. 465–479.
Vicente, Sara, et al. Cosegmentation Revisited: Models and Optimization. Vol. 6312, Springer, 2010, pp. 465–79, doi:10.1007/978-3-642-15552-9_34.

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar