ML Anthology

Integrating Local Classifiers Through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation

Yutian Chen, Andrew Gelfand, Charless C. Fowlkes, Max Welling
ICCV 2011 pp. 2635-2642
doi:10.1109/ICCV.2011.6126553 /iccv/2011/chen2011iccv-integrating/

Abstract

We present a new method to combine possibly inconsistent locally (piecewise) trained conditional models p(y <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">α</sub> |x <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">α</sub> ) into pseudo-samples from a global model. Our method does not require training of a CRF, but instead generates samples by iterating forward a weakly chaotic dynamical system. The new method is illustrated on image segmentation tasks where classifiers based on local appearance cues are combined with pairwise boundary cues.

PDF ICCV Semantic Scholar

Cite

Text

Chen et al. "Integrating Local Classifiers Through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126553

Markdown

[Chen et al. "Integrating Local Classifiers Through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/chen2011iccv-integrating/) doi:10.1109/ICCV.2011.6126553

BibTeX

@inproceedings{chen2011iccv-integrating,
  title     = {{Integrating Local Classifiers Through Nonlinear Dynamics on Label Graphs with an Application to Image Segmentation}},
  author    = {Chen, Yutian and Gelfand, Andrew and Fowlkes, Charless C. and Welling, Max},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2011},
  pages     = {2635-2642},
  doi       = {10.1109/ICCV.2011.6126553},
  url       = {https://mlanthology.org/iccv/2011/chen2011iccv-integrating/}
}