PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Submodularity beyond submodular energies: coupling edges in graph cuts
Stefanie Jegelka and Jeff Bilmes
In: IEEE CVPR, 21-23 June 2011, Colorado Springs, USA.


We propose a new family of non-submodular global energy functions that still use submodularity internally to couple edges in a graph cut. We show it is possible to develop an efficient approximation algorithm that, thanks to the internal submodularity, can use standard graph cuts as a subroutine. We demonstrate the advantages of edge coupling in a natural setting, namely image segmentation. In particular, for fine-structured objects and objects with shading variation, our structured edge coupling leads to significant improvements over standard approaches.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:8771
Deposited By:Stefanie Jegelka
Deposited On:21 February 2012