iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: https://doi.org/10.1007/s10851-016-0659-3
Multicuts and Perturb & MAP for Probabilistic Graph Clustering | Journal of Mathematical Imaging and Vision Skip to main content
Springer Nature Link
Log in

Multicuts and Perturb & MAP for Probabilistic Graph Clustering

  • Published:
Journal of Mathematical Imaging and Vision Aims and scope Submit manuscript

Abstract

We present a probabilistic graphical model formulation for the graph clustering problem. This enables us to locally represent uncertainty of image partitions by approximate marginal distributions in a mathematically substantiated way, and to rectify local data term cues so as to close contours and to obtain valid partitions. We exploit recent progress on globally optimal MAP inference by integer programming and on perturbation-based approximations of the log-partition function, in order to sample clusterings and to estimate marginal distributions of node-pairs both more accurately and more efficiently than state-of-the-art methods. Our approach works for any graphically represented problem instance. This is demonstrated for image segmentation and social network cluster analysis. Our mathematical ansatz should be relevant also for other combinatorial problems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. For \(\theta \in \mathbb {R}^N\) we have \(\mu \in {{\mathrm{{\mathcal {MC}}}}}^\circ (G)\). Boundary points of \({{\mathrm{{\mathcal {MC}}}}}(G)\) are only reached when at least one entry of \(\theta \) is diverging to infinity.

  2. To overcome this problem we will restrict the number of possible labels and exclude thereby some partitions. If the number of used labels is greater or equal than the chromatic number of the graph all partitions are representable.

  3. A graph is called chordal, if each cycle of length strictly larger than 3 have a chord, which is an edge that is not part of the cycle but connects two vertices of the cycle.

  4. http://dblp.uni-trier.de/db/.

  5. For reasons of anonymity, however, we show anonymized results.

References

  1. Aigner, M.: Combinatorial Theory. Springer, Berlin (1997)

    Book  MATH  Google Scholar 

  2. Ambrosio, L., Tortorelli, V.: Approximation of functionals depending on jumps by elliptic functionals via \(\gamma \)-convergence. Commun. Pure Appl. Math. 43(8), 999–1036 (1990)

    Article  MathSciNet  MATH  Google Scholar 

  3. Andres, B., Beier, T., Kappes, J.H.: OpenGM: A C++ library for Discrete Graphical Models. CoRR arXiv:1206.0111 (2012)

  4. Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: Probabilistic image segmentation with closedness constraints. In: ICCV, pp. 2611–2618. IEEE (2011)

  5. Bagon, S., Galun, M.: Large scale correlation clustering optimization. CoRR arXiv:1112.2903 (2011)

  6. Bansal, N., Blum, A., Chawla, S.: Correlation clustering. Mach. Learn. 56(1–3), 89–113 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  7. Beier, T., Hamprecht, F.A., Kappes, J.H.: Fusion moves for correlation clustering. In: IEEE Conference on Computer Vision an Pattern Recognition (CVPR) (2015)

  8. Beier, T., Kroeger, T., Kappes, J.H., Koethe, U., Hamprecht, F.A.: Cut, Glue & cut: a fast, approximate solver for multicut partitioning. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)

  9. Blake, A., Zisserman, A.: Visual Reconstruction. MIT Press, Massachusetts (1987)

    Google Scholar 

  10. Brandes, U., Delling, D., Gaertler, M., Görke, R., Hoefer, M., Nikoloski, Z., Wagner, D.: On modularity clustering. IEEE Trans. Knowl. Data Eng. 20(2), 172–188 (2008). doi:10.1109/TKDE.2007.190689

    Article  MATH  Google Scholar 

  11. Chambolle, A., Cremers, D., Pock, T.: A convex approach to minimal partitions. SIAM J. Imaging Sci. 5(4), 1113–1158 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  12. Chopra, S., Rao, M.: The partition problem. Math. Programm. 59(1–3), 87–115 (1993). doi:10.1007/BF01581239

    Article  MathSciNet  MATH  Google Scholar 

  13. Demaine, E.D., Emanuel, D., Fiat, A., Immorlica, N.: Correlation clustering in general weighted graphs. Theor. Comput. Sci. 361(2), 172–187 (2006). doi:10.1016/j.tcs.2006.05.008. Approximation and Online Algorithms

    Article  MathSciNet  MATH  Google Scholar 

  14. Grötschel, M., Lovász, L., Schrijver, A.: The ellipsoid method and its consequences in combinatorial optimization. Combinatorica 1(2), 169–197 (1981)

    Article  MathSciNet  MATH  Google Scholar 

  15. Gumbel, E.: Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures. Applied Mathematics Series. U. S. Government Printing Office, Washington, DC (1954)

    MATH  Google Scholar 

  16. Hazan, T., Jaakkola, T.: On the partition function and random maximum a-posteriori perturbations. In: ICML. icml.cc / Omnipress (2012)

  17. Hazan, T., Maji, S., Jaakkola, T.S.: On sampling from the Gibbs distribution with random maximum a-posteriori perturbations. In: C.J.C. Burges, L. Bottou, Z. Ghahramani, K.Q. Weinberger (eds.) Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5–8, 2013, Lake Tahoe, Nevada, pp. 1268–1276 (2013)

  18. Hofmann, T., Buhmann, J.: Pairwise data clustering by deterministic annealing. IEEE Trans. Patt. Anal. Mach. Intell. 19(1), 1–14 (1997)

    Article  Google Scholar 

  19. Kannan, R., Vempala, S., Vetta, A.: On clusterings: good, bad and spectral. J. ACM 51(3), 497–515 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  20. Kappes, J.H., Andres, B., Hamprecht, F.A., Schnörr, C., Nowozin, S., Batra, D., Kim, S., Kausler, B.X., Kröger, T., Lellmann, J., Komodakis, N., Savchynskyy, B., Rother, C.: A comparative study of modern inference techniques for structured discrete energy minimization problems. Int. J. Comput. Vis. 115(2), 155–184 (2015). doi:10.1007/s11263-015-0809-x

    Article  MathSciNet  Google Scholar 

  21. Kappes, J.H., Andres, B., Hamprecht, F.A., Schnörr, C., Nowozin, S., Batra, D., Kim, S., Kausler, B.X., Lellmann, J., Komodakis, N., Rother, C.: A comparative study of modern inference techniques for discrete energy minimization problems. In: CVPR (2013)

  22. Kappes, J.H., Speth, M., Andres, B., Reinelt, G., Schnörr, C.: Globally optimal image partitioning by multicuts. In: EMMCVPR, pp. 31–44. Springer (2011)

  23. Kappes, J.H., Speth, M., Reinelt, G., Schnörr, C.: Higher-order segmentation via multicuts. Comput. Vis. Image Underst. 143, 104–119 (2016). Inference and Learning of Graphical Models Theory and Applications in Computer Vision and Image Analysis

    Article  Google Scholar 

  24. Kernighan, B.W., Lin, S.: An efficient heuristic procedure for partitioning graphs. Bell Syst. Tech. J. 49(2), 291–308 (1970)

    Article  MATH  Google Scholar 

  25. Kschischang, F., Member, S., Frey, B.J., Loeliger, Ha: Factor graphs and the sum-product algorithm. IEEE Trans. Inf. Theory 47, 498–519 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  26. Lauritzen, S.L.: Graphical Models. Oxford University Press, Oxford (1996)

    MATH  Google Scholar 

  27. Lellmann, J., Schnörr, C.: Continuous multiclass labeling approaches and algorithms. SIAM J. Imaging Sci. 4(4), 1049–1096 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  28. von Luxburg, U.: A Tutorial on Spectral Clustering. Stat. Comput. 17(4), 395–416 (2007)

    Article  MathSciNet  Google Scholar 

  29. von Luxburg, U.: Clustering stability: an overview. Found. Trends Mach. Learn. 2(3), 235–274 (2009)

    Article  MATH  Google Scholar 

  30. Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of the 8th International Conference on Computer Vision, vol. 2, pp. 416–423 (2001)

  31. Mooij, J.M.: libDAI: a free and open source C++ library for discrete approximate inference in graphical models. J. Mach. Learn. Res. 11, 2169–2173 (2010)

    MATH  Google Scholar 

  32. Nowozin, S., Jegelka, S.: Solution stability in linear programming relaxations: graph partitioning and unsupervised learning. In: Danyluk, A.P., Bottou, L., Littman, M.L. (eds.) ICML, ACM International Conference Proceeding Series, vol. 382, pp. 769–776. ACM (2009)

  33. Orbanz, P., Buhmann, J.: Nonparametric bayesian image segmentation. Int. J. Comput. Vis. 77(1–3), 25–45 (2008)

    Article  Google Scholar 

  34. Papandreou, G., Yuille, A.: Perturb-and-MAP Random Fields: Using Discrete Optimization to Learn and Sample from Energy Models. In: Proceedings of the ICCV (2011)

  35. Papandreou, G., Yuille, A.L.: Perturb-and-map random fields: using discrete optimization to learn and sample from energy models. In: Metaxas, D.N., Quan, L., Sanfeliu, A., Gool, L.J.V. (eds.) ICCV, pp. 193–200. IEEE (2011)

  36. Pätz, T., Kirby, R., Preusser, T.: Ambrosio-Tortorelli segmentation of stochastic images: model extensions, theoretical investigations and numerical methods. Int. J. Comput. Vis. 103(2), 190–212 (2013)

    Article  MathSciNet  MATH  Google Scholar 

  37. Rebagliati, N., Rota Bulo, S., Pelillo, M.: Correlation clustering with stochastic labellings. In: Pelillo, M. (ed.) Similarity-Based Pattern Recognition. LNCS, vol. 7953, pp. 120–133. Springer, Berlin (2013)

    Chapter  Google Scholar 

  38. Shental, N., Zomet, A., Hertz, T., Weiss, Y.: Pairwise clustering and graphical models. In: Thrun, S., Saul, L., Schölkopf, B. (eds.) Advances in Neural Information Processing Systems 16, pp. 185–192. MIT Press, Cambridge, MA (2004)

    Google Scholar 

  39. Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888–905 (2000)

    Article  Google Scholar 

  40. Steutel, F., van Harn, K.: Infinite Divisibility of Probability Distributions on the Real Line. Chapman & Hall/CRC Pure and Applied Mathematics. CRC Press, Boca Raton (2003)

    Book  MATH  Google Scholar 

  41. Wainwright, M.J., Jaakkola, T.S., Willsky, A.S.: Tree-based reparameterization framework for analysis of sum-product and related algorithms. IEEE Trans. Inf. Theory 49(5), 1120–1146 (2003). doi:10.1109/TIT.2003.810642

    Article  MathSciNet  MATH  Google Scholar 

  42. Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Found. Trends\(\textregistered \) Mach. Learn. 1, 1–305 (2008). doi:10.1561/2200000001

  43. Yedidia, J.S., Freeman, W., Weiss, Y.: Constructing free-energy approximations and generalized belief propagation algorithms. IEEE Trans. Inf. Theory 51(7), 2282–2312 (2005). doi:10.1109/TIT.2005.850085

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgments

This work has been supported by the German Research Foundation (DFG) within the programme “Spatio-/Temporal Graphical Models and Applications in Image Analysis”, Grant GRK 1653.

Author information

Authors and Affiliations

  1. HCI, Heidelberg University, Berliner Str. 43, 69120, Heidelberg, Germany

    Jörg Hendrik Kappes

  2. Image & Pattern Analysis Group, Heidelberg University, Im Neuenheimer Feld 205, 69120, Heidelberg, Germany

    Paul Swoboda & Christoph Schnörr

  3. Technische Universität Dresden, 01062, Dresden, Germany

    Bogdan Savchynskyy

  4. Technion - Israel Institute of Technology, Bloomfield Building, Room 503, Technion City, Haifa, 32000, Israel

    Tamir Hazan

Authors
  1. Jörg Hendrik Kappes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paul Swoboda
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Bogdan Savchynskyy
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tamir Hazan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Christoph Schnörr
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jörg Hendrik Kappes.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kappes, J.H., Swoboda, P., Savchynskyy, B. et al. Multicuts and Perturb & MAP for Probabilistic Graph Clustering. J Math Imaging Vis 56, 221–237 (2016). https://doi.org/10.1007/s10851-016-0659-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10851-016-0659-3

Keywords

Search

Navigation