Abstract
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Barnard, K., Duygulu, P., Forsyth, D., Freitas, N., Blei, D., Jordan, M.I.: Matching words and pictures. Journal of Machine Learning Research 3, 1107–1135 (2003)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Bouchard, G., Triggs, B.: The trade-off between generative and discriminative classifiers. In: COMPSTAT (2004)
Dorko, G., Schmid, C.: Selection of scale invariant parts for object class recognition. In: ICCV (2003)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale invariant learning. In: CVPR (2003)
ter Haar Romay, B.M., Florach, L.M.J., Salden, A.H., Viergever, M.A.: Representation of local geometry in the visual system. Biological cybernetics 55, 367–375 (1987)
Holub, A., Perona, P.: A discriminative framework for modelling object classes. In: CVPR (2005)
Kadir, T., Brady, M.: Scale, saliency and image description. International Journal of Computer Vision 45(2), 83–105 (2001)
Koenderink, J.J., van Doorn, A.J.: Representation of local geometry in the visual system. Biological Cybernetics 55, 367–375 (1987)
Kumar, S., Hebert, M.: Discriminative random fields: A discriminative framework for contextual interaction in classification. In: ICCV (2003)
Lowe, D.: Distinctive image features from scale invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. International Journal of Computer Vision 60, 63–86 (2004)
Neal, R., Dayan, P., Hinton, G.E., Zemel, R.S.: The helmholtz machine. Neural Computation, 1022–1037 (1995)
Ng, A.Y., Jordan, M.I.: On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In: Advances in Neural Information Processing Systems 14 (2002)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Net- works of Plausible Inference. Morgan Kaufmann Publishers, San Francisco (1998)
Ulusoy, I., Bishop, C.M.: Generative versus discriminative methods for object recognition. In: CVPR (2005)
Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: ICCV (2003)
Bar-Hillel, A., Hertz, T., Weinshall, D.: Object class recognition by boosting a part-based model. In: CVPR (2005)
Xie, L., Perez, P.: Slightly supervised learning of part-based appearance models. In: IEEE Workshop on Learning in CVPR (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ulusoy, I., Bishop, C.M. (2006). Comparison of Generative and Discriminative Techniques for Object Detection and Classification. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds) Toward Category-Level Object Recognition. Lecture Notes in Computer Science, vol 4170. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11957959_9
Download citation
DOI: https://doi.org/10.1007/11957959_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68794-8
Online ISBN: 978-3-540-68795-5
eBook Packages: Computer ScienceComputer Science (R0)
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.
