ML Anthology

A New Framework for Approximate Labeling via Graph Cuts

Nikos Komodakis, Georgios Tziritas
ICCV 2005 pp. 1018-1025
doi:10.1109/ICCV.2005.14 /iccv/2005/komodakis2005iccv-new/

Abstract

A new framework is presented that uses tools from duality theory of linear programming to derive graph-cut based combinatorial algorithms for approximating NP-hard classification problems. The derived algorithms include alpha-expansion graph cut techniques merely as a special case, have guaranteed optimality properties even in cases where alpha-expansion techniques fail to do so and can provide very tight per-instance suboptimality bounds in all occasions

PDF ICCV Semantic Scholar

Cite

Text

Komodakis and Tziritas. "A New Framework for Approximate Labeling via Graph Cuts." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.14

Markdown

[Komodakis and Tziritas. "A New Framework for Approximate Labeling via Graph Cuts." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/komodakis2005iccv-new/) doi:10.1109/ICCV.2005.14

BibTeX

@inproceedings{komodakis2005iccv-new,
  title     = {{A New Framework for Approximate Labeling via Graph Cuts}},
  author    = {Komodakis, Nikos and Tziritas, Georgios},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1018-1025},
  doi       = {10.1109/ICCV.2005.14},
  url       = {https://mlanthology.org/iccv/2005/komodakis2005iccv-new/}
}