ML Anthology

Hierarchical Segment Support for Categorical Image Labeling

Michael Donoser, Hayko Riemenschneider
ICCVW 2013 pp. 5-8
doi:10.1109/ICCVW.2013.130 /iccvw/2013/donoser2013iccvw-hierarchical/

Abstract

This paper introduces a novel method for categorical image labeling, where each pixel is uniquely assigned to one of a set of unordered, discrete labels. Starting from provided label-depending pixel likelihoods we (a) exploit a segment hierarchy as spatial support to define powerful priors and (b) introduce an efficient and effective inference method, that can be implemented in a few lines of code. Experiments show that competitive labeling accuracy compared to related discrete, continuous, segmentation and filtering approaches is achieved.

ICCVW Semantic Scholar

Cite

Text

Donoser and Riemenschneider. "Hierarchical Segment Support for Categorical Image Labeling." IEEE/CVF International Conference on Computer Vision Workshops, 2013. doi:10.1109/ICCVW.2013.130

Markdown

[Donoser and Riemenschneider. "Hierarchical Segment Support for Categorical Image Labeling." IEEE/CVF International Conference on Computer Vision Workshops, 2013.](https://mlanthology.org/iccvw/2013/donoser2013iccvw-hierarchical/) doi:10.1109/ICCVW.2013.130

BibTeX

@inproceedings{donoser2013iccvw-hierarchical,
  title     = {{Hierarchical Segment Support for Categorical Image Labeling}},
  author    = {Donoser, Michael and Riemenschneider, Hayko},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2013},
  pages     = {5-8},
  doi       = {10.1109/ICCVW.2013.130},
  url       = {https://mlanthology.org/iccvw/2013/donoser2013iccvw-hierarchical/}
}