ML Anthology

Submodularity Beyond Submodular Energies: Coupling Edges in Graph Cuts

Stefanie Jegelka, Jeff A. Bilmes
CVPR 2011 pp. 1897-1904
doi:10.1109/CVPR.2011.5995589 /cvpr/2011/jegelka2011cvpr-submodularity/

Abstract

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 finestructured objects and objects with shading variation, our structured edge coupling leads to significant improvements over standard approaches.

PDF CVPR Semantic Scholar

Cite

Text

Jegelka and Bilmes. "Submodularity Beyond Submodular Energies: Coupling Edges in Graph Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995589

Markdown

[Jegelka and Bilmes. "Submodularity Beyond Submodular Energies: Coupling Edges in Graph Cuts." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/jegelka2011cvpr-submodularity/) doi:10.1109/CVPR.2011.5995589

BibTeX

@inproceedings{jegelka2011cvpr-submodularity,
  title     = {{Submodularity Beyond Submodular Energies: Coupling Edges in Graph Cuts}},
  author    = {Jegelka, Stefanie and Bilmes, Jeff A.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {1897-1904},
  doi       = {10.1109/CVPR.2011.5995589},
  url       = {https://mlanthology.org/cvpr/2011/jegelka2011cvpr-submodularity/}
}