Advertisement

Tighter Relaxations for Higher-Order Models Based on Generalized Roof Duality

  • Johan Fredriksson
  • Carl Olsson
  • Petter Strandmark
  • Fredrik Kahl
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7585)

Abstract

Many problems in computer vision can be turned into a large-scale boolean optimization problem, which is in general NP-hard. In this paper, we further develop one of the most successful approaches, namely roof duality, for approximately solving such problems for higher-order models. Two new methods that can be applied independently or in combination are investigated. The first one is based on constructing relaxations using generators of the submodular function cone. In the second method, it is shown that the roof dual bound can be applied in an iterated way in order to obtain a tighter relaxation. We also provide experimental results that demonstrate better performance with respect to the state-of-the-art, both in terms of improved bounds and the number of optimally assigned variables.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kolmogorov, V., Rother, C.: Minimizing nonsubmodular functions with graph cuts - a review. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1274–1279 (2007)CrossRefGoogle Scholar
  2. 2.
    Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: Int. Conf. Computer Vision, Nice, France (2003)Google Scholar
  3. 3.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)CrossRefGoogle Scholar
  4. 4.
    Schoenemann, T., Kahl, F., Cremers, D.: Curvature regularity for region-based image segmentation and inpainting: A linear programming relaxation. In: Int. Conf. Computer Vision, Kyoto, Japan (2009)Google Scholar
  5. 5.
    Strandmark, P., Kahl, F.: Curvature Regularization for Curves and Surfaces in a Global Optimization Framework. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 205–218. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Lan, X., Roth, S., Huttenlocher, D., Black, M.J.: Efficient Belief Propagation with Learned Higher-Order Markov Random Fields. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part II. LNCS, vol. 3952, pp. 269–282. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Woodford, O., Torr, P.H., Reid, I., Fitzgibbon, A.: Global stereo reconstruction under second-order smoothness priors. IEEE Trans. Pattern Analysis and Machine Intelligence 31, 2115–2128 (2009)CrossRefGoogle Scholar
  8. 8.
    Cremers, D., Grady, L.: Statistical Priors for Efficient Combinatorial Optimization Via Graph Cuts. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part III. LNCS, vol. 3953, pp. 263–274. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Nowozin, S., Lampert, C.H.: Global interactions in random field models: A potential function ensuring connectedness. SIAM J. Imaging Sciences 3, 1048–1074 (2010)MathSciNetzbMATHCrossRefGoogle Scholar
  10. 10.
    Kolmogorov, V.: Generalized roof duality and bisubmodular functions. In: Neural Information Processing Systems (2010)Google Scholar
  11. 11.
    Kahl, F., Strandmark, P.: Generalized roof duality for pseudo-boolean optimization. In: Int. Conf. Computer Vision, Barcelona, Spain (2011)Google Scholar
  12. 12.
    Kahl, F., Strandmark, P.: Generalized roof duality. Discrete Appl. Math. (to appear, 2012)Google Scholar
  13. 13.
    Crama, Y.: Recognition problems for special classes of polynomials in 0-1 variables. Math. Programming 44, 139–155 (1989)MathSciNetzbMATHCrossRefGoogle Scholar
  14. 14.
    Boros, E., Hammer, P., Sun, R., Tavares, G.: A max-flow approach to improved lower bounds for quadratic unconstrained binary optimization (QUBO). Discrete Optimization 5, 501–529 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  15. 15.
    Komodakis, N., Paragios, N.: Beyond pairwise energies: Efficient optimization for higher-order MRFs. In: Conf. Computer Vision and Pattern Recognition, Miami, USA (2009)Google Scholar
  16. 16.
    Strandmark, P., Kahl, F.: Parallel and distributed graph cuts by dual decomposition. In: Conf. Computer Vision and Pattern Recognition, San Francisco, USA (2010)Google Scholar
  17. 17.
    Kohli, P., Kumar, M.P., Torr, P.: P3 & beyond: Move making algorithms for solving higher order functions. IEEE Trans. Pattern Analysis and Machine Intelligence 31, 1645–1656 (2009)CrossRefGoogle Scholar
  18. 18.
    Lempitsky, V., Rother, C., Roth, S., Blake, A.: Fusion moves for Markov random field optimization. IEEE Trans. Pattern Analysis and Machine Intelligence 32, 1392–1405 (2010)CrossRefGoogle Scholar
  19. 19.
    Werner, T.: High-arity interactions, polyhedral relaxations, and cutting plane algorithm for MAP-MRF. In: Conf. Computer Vision and Pattern Recognition, Anchorage, USA (2008)Google Scholar
  20. 20.
    Lu, S., Williams, A.: Roof duality for polynomial 0-1 optimization. Math. Programming 37, 357–360 (1987)MathSciNetzbMATHCrossRefGoogle Scholar
  21. 21.
    Freedman, D., Drineas, P.: Energy minimization via graph cuts: Settling what is possible. In: Conf. Computer Vision and Pattern Recognition, San Diego, USA (2005)Google Scholar
  22. 22.
    Ishikawa, H.: Transformation of general binary MRF minimization to the first order case. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1234–1249 (2011)CrossRefGoogle Scholar
  23. 23.
    Promislow, S.D., Young, V.R.: Supermodular functions on finite lattices. Order 22, 389–413 (2005)MathSciNetzbMATHCrossRefGoogle Scholar
  24. 24.
    Živný, S., Cohen, D.A., Jeavons, P.G.: The expressive power of binary submodular functions. Discrete Appl. Math. 157, 3347–3358 (2009)MathSciNetzbMATHCrossRefGoogle Scholar
  25. 25.
    Fix, A., Grubner, A., Boros, E., Zabih, R.: A graph cut algorithm for higher-order markov random fields. In: Int. Conf. Computer Vision, Barcelona, Spain (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Johan Fredriksson
    • 1
  • Carl Olsson
    • 1
  • Petter Strandmark
    • 1
  • Fredrik Kahl
    • 1
  1. 1.Centre for Mathematical SciencesLund UniversitySweden

Personalised recommendations