ML Anthology

Joint Cuts and Matching of Partitions in One Graph

Tianshu Yu, Junchi Yan, Jieyi Zhao, Baoxin Li
CVPR 2018
doi:10.1109/CVPR.2018.00080 /cvpr/2018/yu2018cvpr-joint/

Abstract

As two fundamental problems, graph cuts and graph matching have been intensively investigated over the decades, resulting in vast literature in these two topics respectively. However the way of jointly applying and solving graph cuts and matching receives few attention. In this paper, we first formalize the problem of simultaneously cutting a graph into two partitions i.e. graph cuts and establishing their correspondence i.e. graph matching. Then we develop an optimization algorithm by updating matching and cutting alternatively, provided with theoretical analysis. The efficacy of our algorithm is verified on both synthetic dataset and real-world images containing similar regions or structures.

PDF CVPR Semantic Scholar

Cite

Text

Yu et al. "Joint Cuts and Matching of Partitions in One Graph." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00080

Markdown

[Yu et al. "Joint Cuts and Matching of Partitions in One Graph." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/yu2018cvpr-joint/) doi:10.1109/CVPR.2018.00080

BibTeX

@inproceedings{yu2018cvpr-joint,
  title     = {{Joint Cuts and Matching of Partitions in One Graph}},
  author    = {Yu, Tianshu and Yan, Junchi and Zhao, Jieyi and Li, Baoxin},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00080},
  url       = {https://mlanthology.org/cvpr/2018/yu2018cvpr-joint/}
}