Discriminative Re-Ranking of Diverse Segmentations

Payman Yadollahpour, Dhruv Batra, Gregory Shakhnarovich

CVPR 2013

doi:10.1109/CVPR.2013.251 /cvpr/2013/yadollahpour2013cvpr-discriminative/

Abstract

This paper introduces a two-stage approach to semantic image segmentation. In the first stage a probabilistic model generates a set of diverse plausible segmentations. In the second stage, a discriminatively trained re-ranking model selects the best segmentation from this set. The re-ranking stage can use much more complex features than what could be tractably used in the probabilistic model, allowing a better exploration of the solution space than possible by simply producing the most probable solution from the probabilistic model. While our proposed approach already achieves state-of-the-art results (48.1%) on the challenging VOC 2012 dataset, our machine and human analyses suggest that even larger gains are possible with such an approach.

PDF CVPR Semantic Scholar

Cite

Text

Yadollahpour et al. "Discriminative Re-Ranking of Diverse Segmentations." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.251

Markdown

[Yadollahpour et al. "Discriminative Re-Ranking of Diverse Segmentations." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/yadollahpour2013cvpr-discriminative/) doi:10.1109/CVPR.2013.251

BibTeX

@inproceedings{yadollahpour2013cvpr-discriminative,
  title     = {{Discriminative Re-Ranking of Diverse Segmentations}},
  author    = {Yadollahpour, Payman and Batra, Dhruv and Shakhnarovich, Gregory},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.251},
  url       = {https://mlanthology.org/cvpr/2013/yadollahpour2013cvpr-discriminative/}
}