ML Anthology

BiCoS: A Bi-Level Co-Segmentation Method for Image Classification

Yuning Chai, Victor S. Lempitsky, Andrew Zisserman
ICCV 2011 pp. 2579-2586
doi:10.1109/ICCV.2011.6126546 /iccv/2011/chai2011iccv-bicos/

Abstract

The objective of this paper is the unsupervised segmentation of image training sets into foreground and background in order to improve image classification performance. To this end we introduce a new scalable, alternation-based algorithm for co-segmentation, BiCoS, which is simpler than many of its predecessors, and yet has superior performance on standard benchmark image datasets.

ICCV Semantic Scholar

Cite

Text

Chai et al. "BiCoS: A Bi-Level Co-Segmentation Method for Image Classification." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126546

Markdown

[Chai et al. "BiCoS: A Bi-Level Co-Segmentation Method for Image Classification." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/chai2011iccv-bicos/) doi:10.1109/ICCV.2011.6126546

BibTeX

@inproceedings{chai2011iccv-bicos,
  title     = {{BiCoS: A Bi-Level Co-Segmentation Method for Image Classification}},
  author    = {Chai, Yuning and Lempitsky, Victor S. and Zisserman, Andrew},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {2579-2586},
  doi       = {10.1109/ICCV.2011.6126546},
  url       = {https://mlanthology.org/iccv/2011/chai2011iccv-bicos/}
}