Abstract
We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method combines these primitives into high-level abstractions. Our appearance-based learning method uses local statistical analysis between features and Expectation-Maximization to identify and code spatial correlations. Spatial correlation is asserted when two features tend to occur at the same relative position of each other. This learning scheme results in a graphical model that constitutes a probabilistic representation of a flexible visual feature hierarchy. For feature detection, evidence is propagated using Belief Propagation. Each message is represented by a Gaussian mixture where each component represents a possible location of the feature. In experiments, the proposed approach demonstrates efficient learning and robust detection of object models in the presence of clutter and occlusion and under view point changes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–130. Springer, Heidelberg (2002)
Cooper, E.E., Wojan, T.J.: Differences in the coding of spatial relations in face identification and basic-level object recognition. J. of Exp. Psychology 26, 470–488 (2000)
Fei-Fei, L., Fergus, R., Perona, P.: A Bayesian approach to unsupervised one-shot learning of object categories. In: ICCV, pp. 1134–1141 (2003)
Harris, C., Stephens, M.: A combined corner and edge detector. In: ALVEY Vision Conference, pp. 147–151 (1988)
Helmer, S., Lowe, D.G.: Object recognition with many local features. In: Workshop on Generative Model Based Vision (GMBV), Washington, D.C. (July 2004)
Lerner, Y., Hendler, T., Ben-Bashat, D., Harel, M., Malach, R.: A hierarchical axis of object processing stages in the human visual cortex. In: Cerebral Cortex, vol. 4, pp. 287–297 (2001)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR, June 2003, vol. 2, pp. 257–263 (2003)
Nene, S.A., Nayar, S.K., Murase, H.: Columbia object image library (coil-100) (1996)
Pearl, J.: Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)
Perona, P., Fergus, R., Zisserman, A.: Object class recognition by unsupervised scaleinvariant learning. In: CVPR, Madison, Wisconsin, June 2003, vol. 2, p. 264 (2003)
Piater, J.H., Grupen, R.A.: Distinctive features should be learned. In: Bülthoff, H.H., Poggio, T.A., Lee, S.-W. (eds.) BMCV 2000. LNCS, vol. 1811, pp. 52–61. Springer, Heidelberg (2000)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2, 1019–1025 (1999)
Schwartz, G.: Estimating the dimension of a model. Ann. Stat. 6(2), 461–464 (1978)
Sudderth, E.B., Ihler, A.T., Freeman, W.T., Willsky, A.S.: Nonparametric belief propagation. In: CVPR, pp. 605–612 (2003)
Wersing, H., Koerner, E.: Unsupervised learning of combination features for hierarchical recognition models. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 1225–1230. Springer, Heidelberg (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Scalzo, F., Piater, J. (2005). Unsupervised Learning of Visual Feature Hierarchies. In: Perner, P., Imiya, A. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2005. Lecture Notes in Computer Science(), vol 3587. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11510888_24
Download citation
DOI: https://doi.org/10.1007/11510888_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26923-6
Online ISBN: 978-3-540-31891-0
eBook Packages: Computer ScienceComputer Science (R0)