Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models

Proceedings of the IEEE International Conference on Computer Vision

Volumn , Issue , 2011, Pages 193-200

  Papandreou, George ^a   Yuille, Alan L ^a,b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b Korea University   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION APPLICATIONS; DISCRETE ENERGIES; DISCRETE OPTIMIZATION; ENERGY FUNCTIONS; ENERGY MODEL; GLOBAL MINIMA; MARKOV CHAIN MONTE CARLO; MARKOV RANDOM FIELD; MODEL PARAMETERS; PROBABILISTIC FRAMEWORK; QUALITATIVE ASPECTS; RANDOM FIELDS; RANDOM SAMPLING; TRAINING DATA;

ALGORITHMS; IMAGE SEGMENTATION;

COMPUTER APPLICATIONS;

EID: 84856654560     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICCV.2011.6126242     Document Type: Conference Paper

References (31)

1. A. Ben-Tal, L. El Ghaoui, and A. Nemirovski. Robust Optimization. Princeton Univ. Press, 2009.
2. J. Besag. Spatial interaction and the statistical analysis of lattice systems. JRSS (B), 36(2): 192-236, 1974.
3. J. Besag. Statistical analysis of non-lattice data. The Statistician, 24(3): 179-195, 1975.
4. S. Boyd and L. Vandenberghe. Convex Optimization. Cambridge Univ. Press, 2004.
5. Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI, 23(11):1222-1239,2001.
6. P. Felzenszwalb and O. Veksler. Tiered scene labeling with dynamic programming. In Proc. CVPR, 20 I O.
7. S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. PAMI, 6(6):721-741,1984.
8. L. Grady. Random walks for image segmentation. IEEE Trans. PAMI, 28(11):1768-1783, 2006.
9. D. Gusfield and R. Irving. The Stable Marriage Problem. MIT Press, 1989.
10. G. Hinton. Training products of experts by minimizing contrastive divergence. Neur. Comp., 14(8):1771-1800,2002.
11. G. Hinton and T. Sejnowski. Optimal perceptual inference. In Proc. CVPR, pages 448-453, 1983.
12. D. Hoiem, A. Efros, and M. Hebert. Recovering surface layout from an image. IJCV, 75(1):151-172, 2007.
13. J. Kleinberg and E. Tardos. Algorithm Design. Addison-Wesley, 2006.
14. P. Kohli and P. Torr. Measuring uncertainty in graph cut solutions. Compo Vision Image Underst., 112(1):30-38,2008.
15. D. Koller and N. Friedman. Probabilistic Graphical Models. MIT Press, 2009.
16. V. Kolmogorov and C. Rother. Minimizing non-submodular functions with graph cuts - a review. IEEE Trans. PAMI, 29(7):1274-1279, July 2007.
17. V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts? IEEE Trans. PAMI, 26(2): 147-159,2004.
18. D. Kuzmin and M.K. Warmuth. Optimum follow the leader algorithm. In Proc. COLT, pages 684-686, 2005.
19. Y. LeCun, S. Chopra, R. Hadsell, M. Ranzato, and F.-J. Huang. A tutorial on energy-based learning. In Predicting Structured Data. MIT Press, 2007.
20. G. Papandreou and A. Yuille. Gaussian sampling by local perturbations. In Proc. NIPS, 2010.
21. J. Propp and D. Wilson. Exact sampling with coupled Markov chains and applications to statistical mechanics. Random Struc. Algor., 9( I ):223-252, 1996.
22. C. Rother, V. Kolmogorov, and A. Blake. Grabcut: Interactive foreground extraction using iterated graph cuts. In Proc. SIGGRAPH, pages 309-314, 2004.
23. C. Rother, V. Kolmogorov, Y. Boykov, and A. Blake. Interactive foreground extraction using graph cut. In Advances in Markov Random Fields for Vision and Image Processing. MIT Press, 2011.
24. U. Schmidt, Q. Gao, and S. Roth. A generative perspective on MRFs in low-level vision. In Proc. CVPR, 2010.
25. F. Steutel and K. Van Harn. Infinite divisibility of probability distributions on the real line. Dekker, 2004.
26. M. Szummer, P. Kohli, and D. Hoiem. Learning CRFs using graph cuts. In Proc. ECCV, pages 582-595, 2008.
27. B. Taskar, C. Guestrin, and D. Koller. Max-margin Markov networks. In Proc. NIPS, 2003.
28. M. Wainwright, T. Jaakkola, and A. Willsky. MAP estimation via agreement on trees: Message-passing and linear programming. IEEE Trans. In! Theory, 51(11):3697-3717, 2005.
29. M. Welling. Herding dynamical weights to learn. In Proc. ICML, pages 1121-1128,2009.
30. O. Woodford, C. Rother, and V. Kolmogorov. A global perspective on MAP inference for low-level vision. In Proc. ICCV, pages 2319-2326, 2009.
31. S.-C. Zhu, Y. Wu, and D. Mumford. Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling. IJCV, 27(2): 107-126, 1998.