MATLAB Code for Factorized Graph Matching (FGM)

Description

This page contains software and instructions for factorized graph matching (FGM) [1] [2]. In addition, we include the following state-of-the-arts methods as baselines:

spectral matching (SM) [3],
spectral matching with affine constraints (SMAC) [4],
graduated assignment (GA) [5],
probabilistic matching (PM) [6],
integer projected fixed point method (IPFP) [7],
re-weighted random walk matching (RRWM) [8].

==========
References
==========
[1] F. Zhou and F. De la Torre, “Deformable Graph Matching,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

[2] F. Zhou and F. De la Torre, “Factorized Graph Matching,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.

[3] M. Leordeanu and M. Hebert, “A spectral technique for correspondence problems using pairwise constraints,” in International Conference on Computer Vision (ICCV), 2005.

[4] T. Cour, P. Srinivasan and J. Shi, “Balanced Graph Matching“, in Advances in Neural Information Processing Systems (NIPS), 2006.

[5] S. Gold and A. Rangarajan, “A Graduated Assignment Algorithm for Graph Matching”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 1996.

[6] R. Zass and A. Shashua, “Probabilistic Graph and Hypergraph Matching”, in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.

[7] M. Leordeanu, M. Hebert and R. Sukthankar, “An Integer Projected Fixed Point Method for Graph Matching and MAP Inference“, in Advances in Neural Information Processing Systems (NIPS), 2009.

[8] M. Cho, J. Lee and K. Lee, “Reweighted Random Walks for Graph Matching“, in European Conference on Computer Vision (ECCV), 2010.

Efficient Graph-Based Image Segmentation