Subgraph learning for graph matching

Abstract Graph matching is a powerful tool for computer vision, distance measure and machine learning. However, many factors influences the accuracy of matching. The outliers is a key problem in the process of matching. In this paper, a novel approach is proposed to handle graph matching problem based on Markov Chain Monte Carlo framework. By constructing a target distribution, the proposed can perform a process of sampling to maximize the graph matching objective. In this process, our method can effectively save matching pairwise under one-to-one matching constraints and also avoid the effect of outliers and deformation. The corresponding experiments on synthetic graphs, real images and view-based 3D model retrieval demonstrate the superiority of the proposed method.

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

[2]  Yu Tian,et al.  Joint Optimization for Consistent Multiple Graph Matching , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Minsu Cho,et al.  Reweighted Random Walks for Graph Matching , 2010, ECCV.

[4]  Xiaojun Chang,et al.  Semisupervised Feature Analysis by Mining Correlations Among Multiple Tasks , 2014, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[7]  Kamil Adamczewski,et al.  Subgraph matching using compactness prior for robust feature correspondence , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Lei Wang,et al.  Improving Graph Matching via Density Maximization , 2013, 2013 IEEE International Conference on Computer Vision.

[9]  Huchuan Lu,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON IMAGE PROCESSING 1 Online Object Tracking with Sparse Prototypes , 2022 .

[10]  Weizhi Nie,et al.  Clique-graph matching by preserving global & local structure , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Dieter Fox,et al.  Unsupervised Feature Learning for RGB-D Based Object Recognition , 2012, ISER.

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

[13]  Minsu Cho,et al.  Hyper-graph matching via reweighted random walks , 2011, CVPR 2011.

[14]  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.

[15]  Yue Gao,et al.  Camera Constraint-Free View-Based 3-D Object Retrieval , 2012, IEEE Transactions on Image Processing.

[16]  Ming-Hsuan Yang,et al.  Object Tracking Benchmark , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Yue Gao,et al.  3-D Object Retrieval and Recognition With Hypergraph Analysis , 2012, IEEE Transactions on Image Processing.

[18]  Mohamed Daoudi,et al.  A Bayesian 3-D Search Engine Using Adaptive Views Clustering , 2007, IEEE Transactions on Multimedia.

[19]  Jean Ponce,et al.  A Tensor-Based Algorithm for High-Order Graph Matching , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Xuan Song,et al.  Learning Graph Matching: Oriented to Category Modeling from Cluttered Scenes , 2013, 2013 IEEE International Conference on Computer Vision.

[21]  Marco Gori,et al.  Exact and approximate graph matching using random walks , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Barend J. van Wyk,et al.  A POCS-Based Graph Matching Algorithm , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Yosi Keller,et al.  A Probabilistic Approach to Spectral Graph Matching , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Yuting Su,et al.  Graph-based characteristic view set extraction and matching for 3D model retrieval , 2015, Inf. Sci..

[25]  Yue Gao,et al.  View-based 3D object retrieval by bipartite graph matching , 2012, ACM Multimedia.

[26]  Francesc Serratosa,et al.  Interactive graph-matching using active query strategies , 2015, Pattern Recognit..

[27]  Horst Bunke,et al.  Efficient subgraph matching using topological node feature constraints , 2015, Pattern Recognit..

[28]  Guillermo Sapiro,et al.  Graph Matching: Relax at Your Own Risk , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Francesc Serratosa,et al.  Learning graph-matching edit-costs based on the optimality of the oracle's node correspondences , 2015, Pattern Recognit. Lett..

[30]  Fernando De la Torre,et al.  Factorized Graph Matching , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[32]  Yi Yang,et al.  Bi-Level Semantic Representation Analysis for Multimedia Event Detection , 2017, IEEE Transactions on Cybernetics.

[33]  Yi Yang,et al.  Semantic Pooling for Complex Event Analysis in Untrimmed Videos , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Shuicheng Yan,et al.  Fast Detection of Dense Subgraphs with Iterative Shrinking and Expansion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.