DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems

In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original n×n-dimensional variable to an n2×n2-dimensional variable, which limits their practical applicability. In contrast, here we present a lifting-free convex relaxation that is provably at least as tight as existing (lifting-free) convex relaxations. We demonstrate experimentally that our approach is superior to existing convex and non-convex methods for various problems, including image arrangement and multi-graph matching.

[1]  Nair Maria Maia de Abreu,et al.  A survey for the quadratic assignment problem , 2007, Eur. J. Oper. Res..

[2]  Nikos Paragios,et al.  Alternating Direction Graph Matching , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Dimitri P. Bertsekas,et al.  Network optimization : continuous and discrete models , 1998 .

[4]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[5]  J. Munkres.  ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[6]  Vikas Singh,et al.  Solving the multi-way matching problem by permutation synchronization , 2013, NIPS.

[7]  Franz Rendl,et al.  A New Lower Bound Via Projection for the Quadratic Assignment Problem , 1992, Math. Oper. Res..

[8]  Carlos D. Castillo,et al.  Biconvex Relaxation for Semidefinite Programming in Computer Vision , 2016, ECCV.

[9]  Teofilo F. Gonzalez,et al.  P-Complete Approximation Problems , 1976, J. ACM.

[10]  Anton van den Hengel,et al.  A Fast Semidefinite Approach to Solving Binary Quadratic Problems , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Abdel Nasser,et al.  A Survey of the Quadratic Assignment Problem , 2014 .

[12]  Mauro Dell'Amico,et al.  Assignment Problems , 1998, IFIP Congress: Fundamentals - Foundations of Computer Science.

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

[14]  Alain Billionnet,et al.  Improving the performance of standard solvers for quadratic 0-1 programs by a tight convex reformulation: The QCR method , 2009, Discret. Appl. Math..

[15]  A. S. Lewis,et al.  Derivatives of Spectral Functions , 1996, Math. Oper. Res..

[16]  Chunhua Shen,et al.  Large-Scale Binary Quadratic Optimization Using Semidefinite Relaxation and Applications , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Timothée Cour.  Convex Relaxations for Markov Random Field MAP estimation , 2008 .

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

[19]  Henry Wolkowicz,et al.  A Low-Dimensional Semidefinite Relaxation for the Quadratic Assignment Problem , 2009, Math. Oper. Res..

[20]  Henry Wolkowicz,et al.  Convex Relaxations of (0, 1)-Quadratic Programming , 1995, Math. Oper. Res..

[21]  Carsten Rother,et al.  A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Leonidas J. Guibas,et al.  Consistent Shape Maps via Semidefinite Programming , 2013, SGP '13.

[23]  Henry Wolkowicz,et al.  ADMM for the SDP relaxation of the QAP , 2015, Math. Program. Comput..

[24]  Edwin R. Hancock,et al.  Multiple graph matching with Bayesian inference , 1997, Pattern Recognit. Lett..

[25]  Panos M. Pardalos,et al.  Quadratic Assignment Problem , 1997, Encyclopedia of Optimization.

[26]  Jun Wang,et al.  Consistency-Driven Alternating Optimization for Multigraph Matching: A Unified Approach , 2015, IEEE Transactions on Image Processing.

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

[28]  Henry Wolkowicz,et al.  On Lagrangian Relaxation of Quadratic Matrix Constraints , 2000, SIAM J. Matrix Anal. Appl..

[29]  Etienne de Klerk,et al.  A New Semidefinite Programming Relaxation for the Quadratic Assignment Problem and Its Computational Perspectives , 2015, INFORMS J. Comput..

[30]  Stephen DiVerdi,et al.  IsoMatch: Creating Informative Grid Layouts , 2015, Comput. Graph. Forum.

[31]  Heinz H. Bauschke,et al.  Convex Analysis and Monotone Operator Theory in Hilbert Spaces , 2011, CMS Books in Mathematics.

[32]  T. Koopmans,et al.  Assignment Problems and the Location of Economic Activities , 1957 .

[33]  Jean Ponce,et al.  Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[34]  Hongyuan Zha,et al.  Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[36]  Alexandre d'Aspremont,et al.  Convex Relaxations for Permutation Problems , 2013, SIAM J. Matrix Anal. Appl..

[37]  Amit Singer,et al.  Semidefinite programming approach for the quadratic assignment problem with a sparse graph , 2017, Computational Optimization and Applications.

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

[39]  Guillermo Sapiro,et al.  On spectral properties for graph matching and graph isomorphism problems , 2014, ArXiv.

[40]  Wei Wei,et al.  Pairwise Matching through Max-Weight Bipartite Belief Propagation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Fernando De la Torre,et al.  Factorized Graph Matching , 2016, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  Johan Thunberg,et al.  A solution for multi-alignment by transformation synchronisation , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Jiming Peng,et al.  A new relaxation framework for quadratic assignment problems based on matrix splitting , 2010, Math. Program. Comput..

[44]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[45]  Leon Hirsch,et al.  Fundamentals Of Convex Analysis , 2016 .

[46]  Bogdan Savchynskyy,et al.  A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problems , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Vladimir Kolmogorov,et al.  A Dual Decomposition Approach to Feature Correspondence , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  Kim-Chuan Toh,et al.  Semi-definite programming relaxation of quadratic assignment problems based on nonredundant matrix splitting , 2015, Comput. Optim. Appl..

[49]  Yaron Lipman,et al.  DS++ , 2017, ACM Trans. Graph..

[50]  Nikos Vlassis,et al.  Fast correspondences for statistical shape models of brain structures , 2016, SPIE Medical Imaging.

[51]  Patrick Pérez,et al.  MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[52]  Bo Jiang,et al.  Binary Constraint Preserving Graph Matching , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[53]  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.

[54]  Vladimir G. Kim,et al.  Entropic metric alignment for correspondence problems , 2016, ACM Trans. Graph..

[55]  Franz Rendl,et al.  Semidefinite Programming Relaxations for the Quadratic Assignment Problem , 1998, J. Comb. Optim..

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

[57]  Daniel Cremers,et al.  Product Manifold Filter: Non-rigid Shape Correspondence via Kernel Density Estimation in the Product Space , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[58]  Ronen Basri,et al.  Tight relaxation of quadratic matching , 2015, SGP '15.

[59]  Y. Aflalo,et al.  On convex relaxation of graph isomorphism , 2015, Proceedings of the National Academy of Sciences.

[60]  Panos M. Pardalos,et al.  The Quadratic Assignment Problem: A Survey and Recent Developments , 1993, Quadratic Assignment and Related Problems.