On the Convergence of Graph Matching: Graduated Assignment Revisited

  • Yu Tian
  • Junchi Yan
  • Hequan Zhang
  • Ya Zhang
  • Xiaokang Yang
  • Hongyuan Zha
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7574)


We focus on the problem of graph matching that is fundamental in computer vision and machine learning. Many state-of-the-arts frequently formulate it as integer quadratic programming, which incorporates both unary and second-order terms. This formulation is in general NP-hard thus obtaining an exact solution is computationally intractable. Therefore most algorithms seek the approximate optimum by relaxing techniques. This paper commences with the finding of the “circular” character of solution chain obtained by the iterative Gradient Assignment (via Hungarian method) in the discrete domain, and proposes a method for guiding the solver converging to a fixed point, resulting a convergent algorithm for graph matching in discrete domain. Furthermore, we extend the algorithms to their counterparts in continuous domain, proving the classical graduated assignment algorithm will converge to a double-circular solution chain, and the proposed Soft Constrained Graduated Assignment (SCGA) method will converge to a fixed (discrete) point, both under wild conditions. Competitive performances are reported in both synthetic and real experiments.


Graph Match Quadratic Assignment Problem Discrete Domain Continuous Domain Spectral Match 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. IJPRAI (2004)Google Scholar
  2. 2.
    Gold, S., Rangarajan, A.: A graduated assignment algorithm for graph matching. PAMI (1996)Google Scholar
  3. 3.
    Leordeanu, M., Hebert, M.: A Spectral Technique for Correspondence Problems using Pairwise Constraints. In: ICCV (2005)Google Scholar
  4. 4.
    Cho, M., Lee, J., Lee, K.M.: Reweighted Random Walks for Graph Matching. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 492–505. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Leordeanu, M., Herbert, M.: An integer projected fixed point method for graph matching and map inference. In: NIPS (2009)Google Scholar
  6. 6.
    Gold, S., Rangarajan, A.: Softmax to softassign: neural network algorithms for combinatorial optimization. J. Artif. Neural Netw., 3810–399 (1995)Google Scholar
  7. 7.
    Rangarajan, A., Yuille, A.: Convergence properties of the softassign quadratic assignment algorithm. Neural Computation (1999)Google Scholar
  8. 8.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Research Logistics Quarterly 2(1-2), 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Christmas, W., Kittler, J., Petrou, M.: Structural matching in computer vision using probabilistic relaxation. PAMI 19(6), 634–648 (1997)CrossRefGoogle Scholar
  10. 10.
    Wilson, R., Hancock, E.: Structural matching by discrete relaxation. IEEE Trans. Pattern Anal. Mach. Intell. 17(8), 749–764 (1995)CrossRefGoogle Scholar
  11. 11.
    Cour, T., Srinivasan, P., Shi, J.: Balanced Graph Matching. In: NIPS (2006)Google Scholar
  12. 12.
    Lee, J., Cho, M., Lee, K.M.: Hyper-graph Matching via Reweighted RandomWalks. In: CVPR (2011)Google Scholar
  13. 13.
    Kosowsky, J.J., Yuille, A.L.: The Invisible Hand Algorithm: Solving the Assignment Problem With Statistical Physics. Neural Networks 7(3) (1994)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yu Tian
    • 1
  • Junchi Yan
    • 1
  • Hequan Zhang
    • 3
  • Ya Zhang
    • 1
  • Xiaokang Yang
    • 1
  • Hongyuan Zha
    • 2
  1. 1.Shanghai Jiao Tong UniversityShanghaiChina
  2. 2.Georgia Institute of TechnologyAtlantaUSA
  3. 3.Beijing Institute of TechnologyBeijingChina

Personalised recommendations