The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.01 - Jan. (2014 vol.36)
pp: 157-170
Christopher Zach , Microsoft Res. Cambridge, Cambridge, UK
Christian Hane , Comput. Vision & Geometry Group, ETH Zurich, Zurich, Switzerland
Marc Pollefeys , Comput. Vision & Geometry Group, ETH Zurich, Zurich, Switzerland
ABSTRACT
In this work, we present a unified view on Markov random fields (MRFs) and recently proposed continuous tight convex relaxations for multilabel assignment in the image plane. These relaxations are far less biased toward the grid geometry than Markov random fields on grids. It turns out that the continuous methods are nonlinear extensions of the well-established local polytope MRF relaxation. In view of this result, a better understanding of these tight convex relaxations in the discrete setting is obtained. Further, a wider range of optimization methods is now applicable to find a minimizer of the tight formulation. We propose two methods to improve the efficiency of minimization. One uses a weaker, but more efficient continuously inspired approach as initialization and gradually refines the energy where it is necessary. The other one reformulates the dual energy enabling smooth approximations to be used for efficient optimization. We demonstrate the utility of our proposed minimization schemes in numerical experiments. Finally, we generalize the underlying energy formulation from isotropic metric smoothness costs to arbitrary nonmetric and orientation dependent smoothness terms.
INDEX TERMS
approximate inference, Markov random fields, continuous labeling problems, convex relaxation,
CITATION
Christopher Zach, Christian Hane, Marc Pollefeys, "What Is Optimized in Convex Relaxations for Multilabel Problems: Connecting Discrete and Continuously Inspired MAP Inference", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.36, no. 1, pp. 157-170, Jan. 2014, doi:10.1109/TPAMI.2013.105
REFERENCES
[1] V. Kolmogorov, "Convergent Tree-Reweighted Message Passing for Energy Minimization," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 10, pp. 1568-1583, Oct. 2006.
[2] A. Globerson and T. Jaakkola, "Fixing Max-Product: Convergent Message Passing Algorithms for MAP LP-Relaxations," Proc. Neural Information Processing Systems, 2007.
[3] T. Werner, "A Linear Programming Approach to Max-Sum Problem: A Review," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 7, pp. 1165-1179, July 2007.
[4] Y. Weiss, C. Yanover, and T. Meltzer, "MAP Estimation Linear Programming and Belief Propagation with Convex Free Energies," Proc. 23rd Ann. Conf. Uncertainty in Artificial Intelligence, 2007.
[5] D. Mumford and J. Shah, "Optimal Approximation by Piecewise Smooth Functions and Associated Variational Problems," Comm. Pure and Applied Math., vol. 42, pp. 577-685, 1989.
[6] G. Alberti, G. Bouchitté, and G.D. Maso, "The Calibration Method for the Mumford-Shah Functional and Free-Discontinuity Problems," Calculus Variations and Partial Differential Equations, vol. 16, no. 3, pp. 299-333, 2003.
[7] A. Chambolle, D. Cremers, and T. Pock, "A Convex Approach for Computing Minimal Partitions," technical report, Ecole Polytechnique, 2008.
[8] T. Pock, A. Chambolle, D. Cremers, and H. Bischof, "A Convex Relaxation Approach for Computing Minimal Partitions," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
[9] M.J. Wainwright and M.I. Jordan, "Graphical Models, Exponential Families, and Variational Inference," Foundations and Trends in Machine Learning, vol. 1, pp. 1-305, 2008.
[10] J. Lellmann and C. Schnörr, "Continuous Multiclass Labeling Approaches and Algorithms," technical report, Heidelberg Univ., 2010.
[11] E. Strekalovskiy, B. Goldluecke, and D. Cremers, "Tight Convex Relaxations for Vector-Valued Labeling Problems," Proc. IEEE Int'l Conf. Computer Vision, 2011.
[12] C. Zach, D. Gallup, J.-M. Frahm, and M. Niethammer, "Fast Global Labeling for Real-Time Stereo Using Multiple Plane Sweeps," Proc. Vision, Modeling, and Visualization Workshop, 2008.
[13] Y. Boykov, O. Veksler, and R. Zabih, "Fast Approximate Energy Minimization via Graph Cuts," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 11, pp. 1222-1239, Nov. 2001.
[14] C. Zach, C. Häne, and M. Pollefeys, "What Is Optimized in Tight Convex Relaxations for Multi-Label Problems?" Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2012.
[15] J. Borwein and A.S. Lewis, Convex Analysis and Nonlinear Optimization: Theory and Examples. Springer, 2000.
[16] R.T. Rockafellar, Convex Analysis, (Princeton Landmarks in Mathematics and Physics). Princeton Univ. Press, Dec. 1996.
[17] H. Ishikawa, "Exact Optimization for Markov Random Fields with Convex Priors," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1333-1336, Oct. 2003.
[18] D. Schlesinger, "Exact Solution of Permuted Submodular Minsum Problems," Proc. Sixth Int'l Conf. Energy Minimization Methods Computer Vision and Pattern Recognition, pp. 28-38, 2007.
[19] D. Sontag and T. Jaakkola, "New Outer Bounds on the Marginal Polytope," Proc. Neural Information Processing Systems, 2007.
[20] D. Sontag, T. Meltzer, A. Globerson, T. Jaakkola, and Y. Weiss, "Tightening LP Relaxations for MAP Using Message Passing," Proc. 24th Conf. Ann. Conf. Uncertainty in Artificial Intelligence, 2008.
[21] T. Werner, "Revisiting the Linear Programming Relaxation Approach to Gibbs Energy Minimization and Weighted Constraint Satisfaction," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 8, pp. 1474-1488, Aug. 2010.
[22] J.P. Boyle and R.L. Dykstra, "A Method For Finding Projections onto the Intersection of Convex Sets in Hilbert Spaces," Advances in Order Restricted Statistical Inference, pp. 28-47, Springer-Verlag, 1986.
[23] M. Wainwright and M.I. Jordan, "Log-Determinant Relaxation for Approximate Inference in Discrete Markov Random Fields," IEEE Trans. Signal Processing, vol. 54, no. 6, pp. 2099-2109, June 2006.
[24] N. Komodakis, N. Paragios, and G. Tziritas, "MRF Optimization via Dual Decomposition: Message-Passing Revisited," Proc. IEEE Int'l Conf. Computer Vision, 2007.
[25] T. Hazan and A. Shashua, "Norm-Product Belief Propagation: Primal-Dual Message-Passing for LP-Relaxation and Approximate-Inference," IEEE Trans. Information Theory, vol. 56, no. 12, pp. 6294-6316, Dec. 2010.
[26] Y. Boykov and V. Kolmogorov, "Computing Geodesics and Minimal Surfaces via Graph Cuts," Proc. Ninth IEEE Int'l Conf. Computer Vision, pp. 26-33, 2003.
[27] J. Lellmann, D. Breitenreicher, and C. Schnörr, "Fast and Exact Primal-Dual Iterations for Variational Problems in Computer Vision," Proc. 11th European Conf. Computer Vision, 2010.
[28] J. Eckstein and D. Bertsekas, "On the Douglas-Rachford Splitting Method and the Proximal Point Algorithm for Maximal Monotone Operators," Math. Programming, vol. 55, pp. 293-318, 1992.
[29] P.L. Combettes and J.-C. Pesquet, "Proximal Splitting Methods in Signal Processing," Fixed-Point Algorithms for Inverse Problems in Science and Eng., pp. 185-212, Springer, 2011.
[30] A. Chambolle and T. Pock, "A First-Order Primal-Dual Algorithm for Convex Problems with Applications to Imaging," J. Math. Imaging and Vision, pp. 1-26, 2010.
[31] Y. Nesterov, "Smooth Minimization of Non-Smooth Functions," Math. Programming, vol. 103, pp. 127-152, 2005.
[32] V. Jojic, S. Gould, and D. Koller, "Accelerated Dual Decomposition for MAP Inference," Proc. Int'l Conf. Machine Learning, pp. 503-510, 2010.
[33] B. Savchynskyy, J.H. Kappes, S. Schmidt, and C. Schnörr, "A Study of Nesterov's Scheme for Lagrangian Decomposition and MAP Labeling," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1817-1823, 2011.
[34] A. Beck and M. Teboulle, "A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems," SIAM J. Imaging Sciences, vol. 2, pp. 183-202, 2009.
[35] E. Strekalovskiy and D. Cremers, "Generalized Ordering Constraints for Multilabel Optimization," Proc. IEEE Int'l Conf. Computer Vision, 2011.
[36] S. Osher and S. Esedoglu, "Decomposition of Images by the Anisotropic Rudin-Osher-Fatemi Model," Comm. Pure Applied Math., vol. 57, pp. 1609-1626, 2004.
[37] C. Zach, M. Niethammer, and J.-M. Frahm, "Continuous Maximal Flows and Wulff Shapes: Application to MRFs," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1911-1918, 2009.
[38] C. Zach, L. Shan, and M. Niethammer, "Globally Optimal Finsler Active Contours," Proc. 31st DAGM Symp. Pattern Recognition, pp. 552-561, 2009.
[39] J. Melonakos, E. Pichon, S. Angenent, and A. Tannenbaum, "Finsler Active Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 3, pp. 412-423, Mar. 2008.
[40] C. Häne, C. Zach, A. Cohen, R. Angst, and M. Pollefeys, "Joint 3D Scene Reconstruction and Class Segmentation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2013.
[41] S. Birchfield and C. Tomasi, "A Pixel Dissimilarity Measure that Is Insensitive to Image Sampling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 4, pp. 401-406, Apr. 1998.
[42] D. Scharstein and R. Szeliski, "High-Accuracy Stereo Depth Maps Using Structured Light," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 195-202, 2003.
38 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool