Fast memory-efficient generalized belief propagation

Authors:
M. Pawan Kumar;P. H. S. Torr
Affiliations:
Department of Computing, Oxford Brookes University, Oxford, UK;Department of Computing, Oxford Brookes University, Oxford, UK
Venue:
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Year:
2006

Citing 5
Cited 3

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
A new point matching algorithm for non-rigid registration

Computer Vision and Image Understanding - Special issue on nonrigid image registration
Learning and Inferring Image Segmentations using the GBP Typical Cut Algorithm

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
OBJ CUT

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
The Representation and Matching of Pictorial Structures

IEEE Transactions on Computers

Fast Generalized Belief Propagation for MAP Estimation on 2D and 3D Grid-Like Markov Random Fields

Proceedings of the 30th DAGM symposium on Pattern Recognition
Faster Algorithms for Max-Product Message-Passing

The Journal of Machine Learning Research
Markov Random Field modeling, inference & learning in computer vision & image understanding: A survey

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Generalized Belief Propagation (gbp) has proven to be a promising technique for performing inference on Markov random fields (mrfs). However, its heavy computational cost and large memory requirements have restricted its application to problems with small state spaces. We present methods for reducing both run time and storage needed by gbp for a large class of pairwise potentials of the mrf. Further, we show how the problem of subgraph matching can be formulated using this class of mrfs and thus, solved efficiently using our approach. Our results significantly outperform the state-of-the-art method. We also obtain excellent results for the related problem of matching pictorial structures for object recognition.