ML Anthology

Are Spatial and Global Constraints Really Necessary for Segmentation?

Aurélien Lucchi, Yunpeng Li, Xavier Boix Bosch, Kevin Smith, Pascal Fua
ICCV 2011 pp. 9-16
doi:10.1109/ICCV.2011.6126219 /iccv/2011/lucchi2011iccv-spatial/

Abstract

Many state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accomplished by introducing additional latent variables to the model, which can greatly increase its complexity. As a result, estimating the model parameters or computing the best maximum a posteriori (MAP) assignment becomes a computationally expensive task.

PDF ICCV Semantic Scholar

Cite

Text

Lucchi et al. "Are Spatial and Global Constraints Really Necessary for Segmentation?." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126219

Markdown

[Lucchi et al. "Are Spatial and Global Constraints Really Necessary for Segmentation?." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/lucchi2011iccv-spatial/) doi:10.1109/ICCV.2011.6126219

BibTeX

@inproceedings{lucchi2011iccv-spatial,
  title     = {{Are Spatial and Global Constraints Really Necessary for Segmentation?}},
  author    = {Lucchi, Aurélien and Li, Yunpeng and Bosch, Xavier Boix and Smith, Kevin and Fua, Pascal},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {9-16},
  doi       = {10.1109/ICCV.2011.6126219},
  url       = {https://mlanthology.org/iccv/2011/lucchi2011iccv-spatial/}
}