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.
This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778. This publication only reflects the authors’ views.
Chapter PDF
Similar content being viewed by others
References
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1998)
Yedidia, J., Freeman, W., Weiss, Y.: Bethe free energy, kikuchi approximations, and belief propagation algorithms. Technical Report TR2001-16, MERL (2001)
Felzenszwalb, P., Huttenlocher, D.: Fast algorithms for large state space HMMs with applications to web usage analysis. In: NIPS, pp. 409–416 (2003)
Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: CVPR, vol. I, pp. 261–268 (2004)
Kumar, M.P., Torr, P.H.S., Zisserman, A.: OBJ CUT. In: CVPR, vol. I, pp. 18–25 (2005)
Shental, N., Zomet, A., Hertz, T., Weiss, Y.: Learning and inferring image segmentation with the GBP typical cut algorithm. In: ICCV, pp. 1243–1250 (2003)
Vogiatzis, G., Torr, P.H.S., Seitz, S., Cipolla, R.: Reconstructing relief surfaces. In: BMVC, pp. 117–126 (2004)
Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. TC 22, 67–92 (1973)
Wainwright, M., Jaakkola, T., Willsky, A.: MAP estimation via agreement on (hyper)trees. Technical Report UCB/CSD-03-1226, UC Berkeley (2003)
Minka, T., Qi, Y.: Tree-structed approximations by expectation propagation. In: NIPS (2003)
Chui, H., Rangarajan, A.: A new point matching algorithm for non-rigid registration. CVIU 89, 114–141 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pawan Kumar, M., Torr, P.H.S. (2006). Fast Memory-Efficient Generalized Belief Propagation. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3954. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744085_35
Download citation
DOI: https://doi.org/10.1007/11744085_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33838-3
Online ISBN: 978-3-540-33839-0
eBook Packages: Computer ScienceComputer Science (R0)