Fast Memory-Efficient Generalized Belief Propagation

  • M. Pawan Kumar
  • P. H. S. Torr
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3954)


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.


  1. 1.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1998)zbMATHGoogle Scholar
  2. 2.
    Yedidia, J., Freeman, W., Weiss, Y.: Bethe free energy, kikuchi approximations, and belief propagation algorithms. Technical Report TR2001-16, MERL (2001)Google Scholar
  3. 3.
    Felzenszwalb, P., Huttenlocher, D.: Fast algorithms for large state space HMMs with applications to web usage analysis. In: NIPS, pp. 409–416 (2003)Google Scholar
  4. 4.
    Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: CVPR, vol. I, pp. 261–268 (2004)Google Scholar
  5. 5.
    Kumar, M.P., Torr, P.H.S., Zisserman, A.: OBJ CUT. In: CVPR, vol. I, pp. 18–25 (2005)Google Scholar
  6. 6.
    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)Google Scholar
  7. 7.
    Vogiatzis, G., Torr, P.H.S., Seitz, S., Cipolla, R.: Reconstructing relief surfaces. In: BMVC, pp. 117–126 (2004)Google Scholar
  8. 8.
    Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. TC 22, 67–92 (1973)Google Scholar
  9. 9.
    Wainwright, M., Jaakkola, T., Willsky, A.: MAP estimation via agreement on (hyper)trees. Technical Report UCB/CSD-03-1226, UC Berkeley (2003)Google Scholar
  10. 10.
    Minka, T., Qi, Y.: Tree-structed approximations by expectation propagation. In: NIPS (2003)Google Scholar
  11. 11.
    Chui, H., Rangarajan, A.: A new point matching algorithm for non-rigid registration. CVIU 89, 114–141 (2003)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • M. Pawan Kumar
    • 1
  • P. H. S. Torr
    • 1
  1. 1.Department of ComputingOxford Brookes UniversityOxfordUK

Personalised recommendations