TY - GEN
T1 - Submodularity beyond submodular energies
T2 - Coupling edges in graph cuts
AU - Jegelka, Stefanie
AU - Bilmes, Jeff
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=80052906787&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2011.5995589
DO - 10.1109/CVPR.2011.5995589
M3 - Conference contribution
AN - SCOPUS:80052906787
SN - 9781457703942
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1897
EP - 1904
BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
PB - IEEE Computer Society
ER -