MRF labeling with a graph-shifts algorithm

Authors:
Jason J. Corso;Zhuowen Tu;Alan Yuille
Affiliations:
Computer Science and Engineering, University at Buffalo, State University of New York;Center for Computational Biology, Laboratory of Neuro Imaging, University of California, Los Angeles;Department of Statistics, University of California, Los Angeles
Venue:
IWCIA'08 Proceedings of the 12th international conference on Combinatorial image analysis
Year:
2008

Citing 12
Cited 0

A revolution: belief propagation in graphs with cycles

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Markov random field modeling in image analysis

Markov random field modeling in image analysis
Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
What Energy Functions Can Be Minimized via Graph Cuts?

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Efficient Belief Propagation for Early Vision

International Journal of Computer Vision
Segmentation of sub-cortical structures by the graph-shifts algorithm

IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Detection and segmentation of pathological structures by the extended graph-shifts algorithm

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
A comparative study of energy minimization methods for markov random fields

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an adaptation of the recently proposed graph-shifts algorithm for labeling MRF problems from low-level vision. Graph-shifts is an energy minimization algorithm that does labeling by dynamically manipulating, or shifting, the parent-child relationships in a hierarchical decomposition of the image. Graph-shifts was originally proposed for labeling using relatively small label sets (e.g., 9) for problems in high-level vision. In the low-level vision problems we consider, there are much larger label sets (e.g., 256). However, the original graph-shifts algorithm does not scale well with the number of labels; for example, the memory requirement is quadratic in the number of labels. We propose four improvements to the graph-shifts representation and algorithm that make it suitable for doing labeling on these large label sets. We implement and test the algorithm on two low-level vision problems: image restoration and stereo. Our results demonstrate the potential for such a hierarchical energy minimization algorithm on low-level vision problems with large label sets.