ML Anthology

Class Segmentation and Object Localization with Superpixel Neighborhoods

Brian Fulkerson, Andrea Vedaldi, Stefano Soatto
ICCV 2009 pp. 670-677
doi:10.1109/ICCV.2009.5459175 /iccv/2009/fulkerson2009iccv-class/

Abstract

We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by aggregating histograms in the neighborhood of each superpixel and then refine our results further by using the classifier in a conditional random field operating on the superpixel graph. Our proposed method exceeds the previously published state-of-the-art on two challenging datasets: Graz-02 and the PASCAL VOC 2007 Segmentation Challenge.

PDF ICCV Semantic Scholar

Cite

Text

Fulkerson et al. "Class Segmentation and Object Localization with Superpixel Neighborhoods." IEEE/CVF International Conference on Computer Vision, 2009. doi:10.1109/ICCV.2009.5459175

Markdown

[Fulkerson et al. "Class Segmentation and Object Localization with Superpixel Neighborhoods." IEEE/CVF International Conference on Computer Vision, 2009.](https://mlanthology.org/iccv/2009/fulkerson2009iccv-class/) doi:10.1109/ICCV.2009.5459175

BibTeX

@inproceedings{fulkerson2009iccv-class,
  title     = {{Class Segmentation and Object Localization with Superpixel Neighborhoods}},
  author    = {Fulkerson, Brian and Vedaldi, Andrea and Soatto, Stefano},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2009},
  pages     = {670-677},
  doi       = {10.1109/ICCV.2009.5459175},
  url       = {https://mlanthology.org/iccv/2009/fulkerson2009iccv-class/}
}