ML Anthology

Data Driven Mean-Shift Belief Propagation for Non-Gaussian MRFs

Minwoo Park, Somesh Kashyap, Robert T. Collins, Yanxi Liu
CVPR 2010 pp. 3547-3554
doi:10.1109/CVPR.2010.5539946 /cvpr/2010/park2010cvpr-data/

Abstract

We introduce a novel data-driven mean-shift belief propagation (DDMSBP) method for non-Gaussian MRFs, which often arise in computer vision applications. With the aid of scale space theory, optimization of non-Gaussian, multimodal MRF models using DDMSBP becomes less sensitive to local maxima. This is a significant improvement over standard BP inference, and extends the range of methods that are computationally tractable. In particular, when pair-wise potentials are Gaussians, the time complexity of DDMSBP becomes bilinear in the numbers of states and nodes in the MRF. Experimental results from simulation and non-rigid deformable neuroimage registration demonstrate that our method is faster and more accurate than state-of-the-art inference algorithms.

CVPR Semantic Scholar

Cite

Text

Park et al. "Data Driven Mean-Shift Belief Propagation for Non-Gaussian MRFs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5539946

Markdown

[Park et al. "Data Driven Mean-Shift Belief Propagation for Non-Gaussian MRFs." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/park2010cvpr-data/) doi:10.1109/CVPR.2010.5539946

BibTeX

@inproceedings{park2010cvpr-data,
  title     = {{Data Driven Mean-Shift Belief Propagation for Non-Gaussian MRFs}},
  author    = {Park, Minwoo and Kashyap, Somesh and Collins, Robert T. and Liu, Yanxi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2010},
  pages     = {3547-3554},
  doi       = {10.1109/CVPR.2010.5539946},
  url       = {https://mlanthology.org/cvpr/2010/park2010cvpr-data/}
}