Unsupervised Learning for Graph Matching

Graph matching is an essential problem in computer vision that has been successfully applied to 2D and 3D feature matching and object recognition. Despite its importance, little has been published on learning the parameters that control graph matching, even though learning has been shown to be vital for improving the matching rate. In this paper we show how to perform parameter learning in an unsupervised fashion, that is when no correct correspondences between graphs are given during training. Our experiments reveal that unsupervised learning compares favorably to the supervised case, both in terms of efficiency and quality, while avoiding the tedious manual labeling of ground truth correspondences. We verify experimentally that our learning method can improve the performance of several state-of-the art graph matching algorithms. We also show that a similar method can be successfully applied to parameter learning for graphical models and demonstrate its effectiveness empirically.

[1]  Shinji Umeyama,et al.  An Eigendecomposition Approach to Weighted Graph Matching Problems , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Jean Ponce,et al.  A tensor-based algorithm for high-order graph matching , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Francis R. Bach,et al.  A Path Following Algorithm for Graph Matching , 2008, ICISP.

[4]  Jianbo Shi,et al.  Solving Markov Random Fields with Spectral Relaxation , 2007, AISTATS.

[5]  Martial Hebert,et al.  An Integer Projected Fixed Point Method for Graph Matching and MAP Inference , 2009, NIPS.

[6]  Michael I. Jordan,et al.  Learning Spectral Clustering , 2003, NIPS.

[7]  Christoph Schnörr,et al.  Probabilistic Subgraph Matching Based on Convex Relaxation , 2005, EMMCVPR.

[8]  Steven Gold,et al.  A Graduated Assignment Algorithm for Graph Matching , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Martial Hebert,et al.  Unsupervised learning for graph matching , 2009, CVPR.

[10]  Xiaofeng Ren,et al.  Learning and Matching Line Aspects for Articulated Objects , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Alexei A. Efros,et al.  Discovering Texture Regularity as a Higher-Order Correspondence Problem , 2006, ECCV.

[12]  L. Pottier,et al.  Optimization of positive generalized polynomials under constraints. , 1998 .

[13]  Philip H. S. Torr,et al.  Solving Markov Random Fields using Semi Definite Programming , 2003, AISTATS.

[14]  Martial Hebert,et al.  Smoothing-based Optimization , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Amnon Shashua,et al.  Probabilistic graph and hypergraph matching , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Jianbo Shi,et al.  Learning spectral graph segmentation , 2005, AISTATS.

[17]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[19]  Christos Faloutsos,et al.  Unsupervised modeling of object categories using link analysis techniques , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Martial Hebert,et al.  Efficient MAP approximation for dense energy functions , 2006, ICML.

[21]  Jitendra Malik,et al.  Shape Matching and Object Recognition , 2006, Toward Category-Level Object Recognition.

[22]  Arcot Sowmya,et al.  Tensor Power Method for Efficient MAP Inference in Higher-order MRFs , 2010, 2010 20th International Conference on Pattern Recognition.

[23]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[24]  Yosi Keller,et al.  Spectral Symmetry Analysis , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Ben Taskar,et al.  Max-Margin Markov Networks , 2003, NIPS.

[26]  Pradeep Ravikumar,et al.  Quadratic programming relaxations for metric labeling and Markov random field MAP estimation , 2006, ICML.

[27]  Mubarak Shah,et al.  Learning 4D action feature models for arbitrary view action recognition , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Tsuhan Chen,et al.  Unsupervised Learning of Hierarchical Semantics of Objects (hSOs) , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Sanjiv Kumar,et al.  Models for learning spatial interactions in natural images , 2004 .

[30]  Tsuhan Chen,et al.  Unsupervised Identification of Multiple Objects of Interest from Multiple Images: dISCOVER , 2007, ACCV.

[31]  Jiebo Luo,et al.  Recognizing realistic actions from videos “in the wild” , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  J. Magnus,et al.  Matrix Differential Calculus with Applications in Statistics and Econometrics , 1991 .

[33]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[34]  Derek Hoiem,et al.  Learning CRFs Using Graph Cuts , 2008, ECCV.

[35]  M. Zaslavskiy,et al.  A Path Following Algorithm for the Graph Matching Problem , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Philip Wolfe,et al.  An algorithm for quadratic programming , 1956 .

[37]  Martial Hebert,et al.  Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  Edwin R. Hancock,et al.  Alignment using Spectral Clusters , 2002, BMVC.

[39]  M. Leordeanu,et al.  Unsupervised learning of object features from video sequences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[40]  Vladimir Kolmogorov,et al.  Feature Correspondence Via Graph Matching: Models and Global Optimization , 2008, ECCV.

[41]  Hans-Peter Seidel,et al.  Performance capture from sparse multi-view video , 2008, ACM Trans. Graph..

[42]  Jianbo Shi,et al.  Balanced Graph Matching , 2006, NIPS.

[43]  Wolfgang Straßer,et al.  On-the-fly scene acquisition with a handy multi-sensor system , 2008, Int. J. Intell. Syst. Technol. Appl..

[44]  William Brendel,et al.  Segmentation as Maximum-Weight Independent Set , 2010, NIPS.

[45]  Christos Faloutsos,et al.  Unsupervised modeling and recognition of object categories with combination of visual contents and geometric similarity links , 2008, MIR '08.