Data driven mean-shift belief propagation for non-Gaussian MRFs

Minwoo Park, Somesh Kashyap, Robert Collins, Yanxi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

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.

Original languageEnglish (US)
Title of host publication2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Pages3547-3554
Number of pages8
DOIs
StatePublished - 2010
Event2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States
Duration: Jun 13 2010Jun 18 2010

Other

Other2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
CountryUnited States
CitySan Francisco, CA
Period6/13/106/18/10

Fingerprint

Computer vision

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Park, M., Kashyap, S., Collins, R., & Liu, Y. (2010). Data driven mean-shift belief propagation for non-Gaussian MRFs. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 (pp. 3547-3554). [5539946] https://doi.org/10.1109/CVPR.2010.5539946
Park, Minwoo ; Kashyap, Somesh ; Collins, Robert ; Liu, Yanxi. / Data driven mean-shift belief propagation for non-Gaussian MRFs. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. pp. 3547-3554
@inproceedings{8d273f44fc4346b7b44a96d1e476a48e,
title = "Data driven mean-shift belief propagation for non-Gaussian MRFs",
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.",
author = "Minwoo Park and Somesh Kashyap and Robert Collins and Yanxi Liu",
year = "2010",
doi = "10.1109/CVPR.2010.5539946",
language = "English (US)",
isbn = "9781424469840",
pages = "3547--3554",
booktitle = "2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010",

}

Park, M, Kashyap, S, Collins, R & Liu, Y 2010, Data driven mean-shift belief propagation for non-Gaussian MRFs. in 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010., 5539946, pp. 3547-3554, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, United States, 6/13/10. https://doi.org/10.1109/CVPR.2010.5539946

Data driven mean-shift belief propagation for non-Gaussian MRFs. / Park, Minwoo; Kashyap, Somesh; Collins, Robert; Liu, Yanxi.

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. p. 3547-3554 5539946.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Data driven mean-shift belief propagation for non-Gaussian MRFs

AU - Park, Minwoo

AU - Kashyap, Somesh

AU - Collins, Robert

AU - Liu, Yanxi

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=77955988501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955988501&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2010.5539946

DO - 10.1109/CVPR.2010.5539946

M3 - Conference contribution

SN - 9781424469840

SP - 3547

EP - 3554

BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010

ER -

Park M, Kashyap S, Collins R, Liu Y. Data driven mean-shift belief propagation for non-Gaussian MRFs. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. p. 3547-3554. 5539946 https://doi.org/10.1109/CVPR.2010.5539946