Abstract
Pairwise Markov random fields are an effective framework for solving many pixel labeling problems in computer vision. However, their performance is limited by their inability to capture higher-order correlations. Recently proposed higher-order models are showing superior performance to their pairwise counterparts. In this paper, we derive two variants of the higher-order lower linear envelop model and show how to perform tractable move-making inference in these models. We propose a novel use of this model for encoding consistency constraints over large sets of pixels. Importantly these pixel sets do not need to be contiguous. However, the consistency model has a large number of parameters to be tuned for good performance. We exploit the structured SVM paradigm to learn optimal parameters and show some practical techniques to overcome huge computation requirements. We evaluate our model on the problems of image denoising and semantic segmentation.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
He, X., Zemel, R., Carreira-Perpinán, M.: Multiscale conditional random fields for image labeling. In: CVPR (2004)
Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)
Hoiem, D., Efros, A., Hebert, M.: Recovering surface layout from an image. International Journal of Computer Vision 75, 151–172 (2007)
Roth, S., Black, M.: Fields of experts. International Journal of Computer Vision 82, 205–229 (2009)
Kohli, P., Kumar, M., Torr, P.: P3 & beyond: Solving energies with higher order cliques. In: CVPR (2007)
Kohli, P., Ladickỳ, L., Torr, P.: Robust higher order potentials for enforcing label consistency. International Journal of Computer Vision 82, 302–324 (2009)
Kohli, P., Kumar, M.: Energy minimization for linear envelope MRFs. In: CVPR (2010)
Ladicky, L., Russell, C., Kohli, P., Torr, P.: Associative hierarchical CRFs for object class image segmentation. In: ICCV (2009)
Szummer, M., Kohli, P., Hoiem, D.: Learning CRFs Using Graph Cuts. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 582–595. Springer, Heidelberg (2008)
Gould, S.: Max-margin learning for lower linear envelope potentials in binary markov random fields. In: ICML (2011)
Komodakis, N.: Efficient training for pairwise or higher order CRFs via dual decomposition. In: CVPR (2011)
Boros, E., Hammer, P.: Pseudo-boolean optimization. Discrete Applied Mathematics 123, 155–225 (2002)
Kolmogorov, V., Zabin, R.: What energy functions can be minimized via graph cuts? PAMI (2004)
Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for markov random fields with smoothness-based priors. PAMI (2008)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. PAMI (2001)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI (2004)
Besag, J.: On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society. Series B (Methodological), 259–302 (1986)
Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)
Taskar, B., Chatalbashev, V., Koller, D., Guestrin, C.: Learning structured prediction models: A large margin approach. In: ICML (2005)
Batra, D., Kohli, P.: Making the right moves: Guiding alpha-expansion using local primal-dual gaps. In: CVPR (2011)
Finley, T., Joachims, T.: Training structural SVMs when exact inference is intractable. In: ICML (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, K., Gould, S. (2012). On Learning Higher-Order Consistency Potentials for Multi-class Pixel Labeling. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7573. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33709-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-33709-3_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33708-6
Online ISBN: 978-3-642-33709-3
eBook Packages: Computer ScienceComputer Science (R0)