Scholars@Duke publication: Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation

Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation

Publication , Conference

Chen, Y; Gelfand, A; Fowlkes, CC; Welling, M

Published in: Proceedings of the IEEE International Conference on Computer Vision

December 1, 2011

We present a new method to combine possibly inconsistent locally (piecewise) trained conditional models p(y αx α) 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. © 2011 IEEE.

Duke Scholars

Author Alan E. Gelfand Statistical Science

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

10.1109/ICCV.2011.6126553

Publication Date

December 1, 2011

Start / End Page

2635 / 2642

Citation

APA

Chicago

ICMJE

MLA

NLM

Chen, Y., Gelfand, A., Fowlkes, C. C., & Welling, M. (2011). Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2635–2642). https://doi.org/10.1109/ICCV.2011.6126553

Chen, Y., A. Gelfand, C. C. Fowlkes, and M. Welling. “Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation.” In Proceedings of the IEEE International Conference on Computer Vision, 2635–42, 2011. https://doi.org/10.1109/ICCV.2011.6126553.

Chen Y, Gelfand A, Fowlkes CC, Welling M. Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation. In: Proceedings of the IEEE International Conference on Computer Vision. 2011. p. 2635–42.

Chen, Y., et al. “Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation.” Proceedings of the IEEE International Conference on Computer Vision, 2011, pp. 2635–42. Scopus, doi:10.1109/ICCV.2011.6126553.

Chen Y, Gelfand A, Fowlkes CC, Welling M. Integrating local classifiers through nonlinear dynamics on label graphs with an application to image segmentation. Proceedings of the IEEE International Conference on Computer Vision. 2011. p. 2635–2642.

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

10.1109/ICCV.2011.6126553

Publication Date

December 1, 2011

Start / End Page

2635 / 2642