Abstract
We present LS-CRF, a new method for training cyclic Conditional Random Fields (CRFs) from large datasets that is inspired by classical closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree topology. Training a CRF with LS-CRF requires only solving a set of independent regression problems, each of which can be solved efficiently in closed form or by an iterative solver. This makes LS-CRF orders of magnitude faster than classical CRF training based on probabilistic inference, and at the same time more flexible and easier to implement than other approximate techniques, such as pseudolikelihood or piecewise training. We apply LS-CRF to the task of semantic image segmentation, showing that it achieves on par accuracy to other training techniques at higher speed, thereby allowing efficient CRF training from very large training sets. For example, training a linearly parameterized pairwise CRF on 150,000 images requires less than one hour on a modern workstation.
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
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. PAMI 34(11) (2012)
Andres, B., Beier, T., Kappes, J.H.: OpenGM: A C++ library for discrete graphical models. ArXiv e-prints 1206.0111 (2012), http://arxiv.org/abs/1206.0111
Arandjelović, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: CVPR (2012)
Besag, J.: Statistical analysis of non-lattice data. The Statistician (1975)
Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. In: NIPS (2007)
Bulatov, A., Grohe, M.: The complexity of partition functions. Theoretical Computer Science 348(2) (2005)
Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM Journal on Scientific Computing (SISC) 16(5), 1190–1208 (1995)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: A large-scale hierarchical image database. In: CVPR (2009)
Domke, J.: Learning graphical model parameters with approximate marginals inference. PAMI (2013)
Domke, J.: Structured learning via logistic regression. In: NIPS (2013)
Everingham, M., van Gool, L., Williams, C., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. IJCV 88(2) (2010)
Finley, T., Joachims, T.: Training structural SVMs when exact inference is intractable. In: ICML (2008)
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Annals of Statistics (2001)
Fulkerson, B., Vedaldi, A., Soatto, S.: Class segmentation and object localization with superpixel neighborhoods. In: ICCV (2009)
Gould, S.: Multiclass pixel labeling with non-local matching constraints. In: CVPR, pp. 2783–2790 (2012)
Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: ICCV (2009)
Gould, S., Zhang, Y.: patchMatchGraph: Building a graph of dense patch correspondences for label transfer. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part V. LNCS, vol. 7576, pp. 439–452. Springer, Heidelberg (2012)
Guillaumin, M., Kuettel, D., Ferrari, V.: ImageNet Auto-annotation with Segmentation Propagation. IJCV (2014)
Kohli, P., Shekhovtsov, A., Rother, C., Kolmogorov, V., Torr, P.: On partial optimality in multi-label MRFs. In: ICML (2008)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. PAMI 28(10) (2006)
Komodakis, N.: Efficient training for pairwise or higher order CRFs via dual decomposition. In: CVPR, pp. 1841–1848 (2011)
Lempitsky, V.S., Vedaldi, A., Zisserman, A.: A pylon model for semantic segmentation. NIPS 24, 1485–1493 (2011)
Meshi, O., Sontag, D., Jaakkola, T., Globerson, A.: Learning efficiently with approximate inference via dual losses (2010)
Nowozin, S., Lampert, C.H.: Structured learning and prediction in computer vision. Foundations and Trends in Computer Graphics and Vision 6 (2011)
Nowozin, S., Rother, C., Bagon, S., Sharp, T., Yao, B., Kohli, P.: Decision tree fields. In: ICCV (2011)
Schroff, F., Criminisi, A., Zisserman, A.: Object class segmentation using random forests. In: BMVC (2008)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. IJCV 81(1) (2009)
Sontag, D., Meshi, O., Globerson, A., Jaakkola, T.S.: More data means less inference: A pseudo-max approach to structured learning. In: NIPS (2010)
Sutton, C., McCallum, A.: Piecewise training of undirected models. In: UAI (2005)
Tighe, J., Lazebnik, S.: SuperParsing: Scalable nonparametric image parsing with superpixels. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 352–365. Springer, Heidelberg (2010)
Trofimov, I., Kornetova, A., Topinskiy, V.: Using boosted trees for click-through rate prediction for sponsored search. In: International Workshop on Data Mining for Online Advertising and Internet Economy (2012)
Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y.: Large margin methods for structured and interdependent output variables. JMLR 6 (2005)
Wainwright, M.J., Jordan, M.I.: Graphical models, exponential families, and variational inference. Foundations and Trends in Machine Learning (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
1 Electronic Supplementary Material
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kolesnikov, A., Guillaumin, M., Ferrari, V., Lampert, C.H. (2014). Closed-Form Approximate CRF Training for Scalable Image Segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8691. Springer, Cham. https://doi.org/10.1007/978-3-319-10578-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-319-10578-9_36
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10577-2
Online ISBN: 978-3-319-10578-9
eBook Packages: Computer ScienceComputer Science (R0)