Abstract
Natural image data shows significant dependencies that should be modeled appropriately to achieve good classification. Such dependencies are commonly referred to as context in Vision. This chapter describes Conditional Random Fields (CRFs) based discriminative models for incorporating context in a principled manner. Unlike the traditional generative Markov Random Fields (MRFs), CRFs allow the use of arbitrarily complex dependencies in the observed data along with datadependent interactions in labels. Fast and robust parameter learning techniques for such models are described. The extensions of the standard binary CRFs to handle problems with multiclass labels or hierarchical context are also discussed. Finally, application of CRFs on contextual object detection, scene segmentation and texture recognition tasks is demonstrated.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
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
Besag, J.: On the statistical analysis of dirty pictures. Journal of Royal Statistical Society B-48, 259–302 (1986)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: Proceedings of the International Conference on Computer Vision (ICCV), vol. I, pp. 105–112 (2001)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE transactions on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Geman, S., Geman, D.: Stochastic relaxation, gibbs distribution and the bayesian restoration of images. IEEE transactions on Pattern Analysis and Machine Intelligence 6, 721–741 (1984)
Greig, D.M., Porteous, B.T., Seheult, A.H.: Exact maximum a posteriori estimation for binary images. Journal of Royal Statistical Society 51(2), 271–279 (1989)
Hammersley, J.M., Clifford, P.: Markov field on finite graph and lattices (unpublished)
He, X., Zemel, R., Carreira-Perpinan, M.: Multiscale Conditional Random Fields for image labelling. In: Proceedings of International Conference on Computer Vision and Pattern Recognition (2004)
Ising, E.: Beitrag zur theorie der ferromagnetismus. Zeitschrift Fur. Physik. 31, 253–258 (1925)
Kumar, S.: Models for Learning Spatial Interactions in Natural Images for Context-Based Classification. PhD Thesis, Carnegie Mellon University, The Robotics Institute, School of Computer Science (2005)
Kumar, S., August, J., Hebert, M.: Exploiting inference for approximate parameter learning in discriminative fields: An empirical study. In: Rangarajan, A., Vemuri, B.C., Yuille, A.L. (eds.) EMMCVPR 2005. LNCS, vol. 3757, pp. 153–168. Springer, Heidelberg (2005)
Kumar, S., Hebert, M.: Discriminative fields for modeling spatial dependencies in natural images. In: Proceedings of the International Conference on Neural Information Processing Systems, NIPS (2003)
Kumar, S., Hebert, M.: Discriminative Random Fields: A discriminative framework for contextual interaction in classification. In: Proceedings of the International Conference on Computer Vision (ICCV), vol. 2, pp. 1150–1157 (2003)
Kumar, S., Hebert, M.: A hierarchical field framework for unified context-based classification. In: Proceedings of the International Conference on Computer Vision, ICCV (2005)
Kumar, S., loui, A.C., Hebert, M.: An observation-constrained generative approach for probabilistic classification of image regions. Image and Vision Computing, Special Issue on Generative Models Based Vision 21, 87–97 (2003)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceedings of the International Conference on Machine Learning (2001)
LeCun, Y., Huang, F.J.: Loss functions for discriminative training of energy-based models. AI-Stats (2005)
Lee, C., Wang, S., Jiao, F., Schuurmans, D., Greiner, R.: Learning to model spatial dependency: semi-supervised discriminative random fields. In: Proceedings of the International Conference on Neural Information Processing Systems Conference, NIPS (2006)
McCullagh, P., Nelder, J.A.: Generalised Linear Models. Chapman and Hall, London (1987)
Qi, Y., Szummer, M., Minka, T.P.: Diagram structure recognition by Bayesian Conditional Random Fields. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition, CVPR (2005)
Quattoni, A., Collins, M., Darrell, T.: Conditional Random Fields for object recognition. In: Proceedings of the International Conference on Neural Information Processing Systems, NIPS (2004)
Torralba, A., Murphy, K.P., Freeman, W.T.: Contextual models for object detection using Boosted Random Fields. In: Proceedings of the International Conference on Neural Information Processing Systems, NIPS (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kumar, S. (2010). Discriminative Graphical Models for Context-Based Classification. In: Cipolla, R., Battiato, S., Farinella, G.M. (eds) Computer Vision. Studies in Computational Intelligence, vol 285. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12848-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-12848-6_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12847-9
Online ISBN: 978-3-642-12848-6
eBook Packages: EngineeringEngineering (R0)