Advertisement

Unsupervised Learning of Visual Feature Hierarchies

  • Fabien Scalzo
  • Justus Piater
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3587)

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.

Keywords

Graphical Model Visual Feature Spatial Relation Interest Point Primitive Feature 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    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)CrossRefGoogle Scholar
  2. 2.
    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)Google Scholar
  3. 3.
    Fei-Fei, L., Fergus, R., Perona, P.: A Bayesian approach to unsupervised one-shot learning of object categories. In: ICCV, pp. 1134–1141 (2003)Google Scholar
  4. 4.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: ALVEY Vision Conference, pp. 147–151 (1988)Google Scholar
  5. 5.
    Helmer, S., Lowe, D.G.: Object recognition with many local features. In: Workshop on Generative Model Based Vision (GMBV), Washington, D.C. (July 2004)Google Scholar
  6. 6.
    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)Google Scholar
  7. 7.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: CVPR, June 2003, vol. 2, pp. 257–263 (2003)Google Scholar
  8. 8.
    Nene, S.A., Nayar, S.K., Murase, H.: Columbia object image library (coil-100) (1996)Google Scholar
  9. 9.
    Pearl, J.: Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)Google Scholar
  10. 10.
    Perona, P., Fergus, R., Zisserman, A.: Object class recognition by unsupervised scaleinvariant learning. In: CVPR, Madison, Wisconsin, June 2003, vol. 2, p. 264 (2003)Google Scholar
  11. 11.
    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)CrossRefGoogle Scholar
  12. 12.
    Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nature Neuroscience 2, 1019–1025 (1999)CrossRefGoogle Scholar
  13. 13.
    Schwartz, G.: Estimating the dimension of a model. Ann. Stat. 6(2), 461–464 (1978)CrossRefGoogle Scholar
  14. 14.
    Sudderth, E.B., Ihler, A.T., Freeman, W.T., Willsky, A.S.: Nonparametric belief propagation. In: CVPR, pp. 605–612 (2003)Google Scholar
  15. 15.
    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)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Fabien Scalzo
    • 1
  • Justus Piater
    • 1
  1. 1.Montefiore InstituteUniversity of LiègeLiègeBelgium

Personalised recommendations