Advertisement

On-line Learning of Object Representations

  • Horst Bischof
  • Aleš Leonardis
Conference paper

Abstract

Radial Basis Function (RBF) networks have been proposed as suitable representations for 3-D objects, in particular, since they can learn view-based representations from a small set of training views. One of the basic questions that arises in the context of RBF networks concerns their complexity, i.e., the number of basis functions that are necessary for a reliable representation, which should balance the accuracy and the robustness. In this paper we propose a systematic approach for building object representations in terms of RBF networks. We studied and designed two procedures: the “off-line” procedure, where the network is constructed after having a complete set of training views of an object, and the “on-line” procedure, where the network is incrementally built as new views of an object arrive.

Keywords

Basis Function Radial Basis Function Object Representation Radial Basis Function Network Stick Figure 
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]
    H. H. Bülthoff and S. Y. Edelman and M. Tarr, How are three-dimensional objects represented in the brain?, A. I. Memo No. 1479, C. B. C. L. Paper No. 96, Massachusetts Institute of Technology, April 1994.Google Scholar
  2. [2]
    S. Chandrasekaran, B.S. Manjunath, Y.F. Wang, J. Winkler, and H. Zhang, An eigenspace update algorithm for image analysis, Technical report, TR CS 96-04, Dept. of Computer Science, Univ. of California, Santa Barbara.Google Scholar
  3. [3]
    F. Girosi, M. Jones, and T. Poggio. Regulariza-tion theory and neural network architectures. Neural Computation 7(2):219–269, 1995.CrossRefGoogle Scholar
  4. [4]
    B. Fritzke. Fast learning with incremental RBF networks. Neural Processing Letters 1(1):2–5, 1994.CrossRefGoogle Scholar
  5. [5]
    Y. L. Le Cun and J. S. Denker and S. A. Solla. Optimal Brain Damage. Advances in Neural Information Processing Systems 2. Ed. D. S. Touretzky. San Mateo, CA: Morgan Kaufmann, pp. 598–605, 1988.Google Scholar
  6. [6]
    B. Hassibi and D. G. Stork. Second Order Derivatives for network Pruning: Optimal Brain Surgeon. In Proceedings of NIPS 5. Ed. S. J. Hanson et al. Morgan Kaufmann, pp. 164–172, 1993.Google Scholar
  7. [7]
    A. Leonardis and H. Bischof. Complexity Optimization of Adaptive RBF Networks. In Proceedings of the ICPR′96 Vol IV pages 654–658, IEEE Computer Society Press, 1996.Google Scholar
  8. [8]
    A. Leonardis, A. Gupta, and R. Bajcsy. Segmentation of range images as the search for geometric parametric models. International Journal of Computer Vision 14:253–277, 1995.CrossRefGoogle Scholar
  9. [9]
    D. Lowe. Adaptive radial basis function nonlin-earities, and the problem of generalisation. In 1st IEE Conference on Artificial Neural Networks pages 171–175. London U.K., 1989.Google Scholar
  10. [10]
    J. Moody and C. Darken. Fast learning in networks of locally tuned processing units. Neural Computation 1(2):281–294, 1989.CrossRefGoogle Scholar
  11. [11]
    S. Mukherjee and S. K. Nayar. Automatic Generation of GRBF networks for visual learning. In Proceedings of the ICCV′95 pages 794–800, 1995.Google Scholar
  12. [12]
    M. J. Orr. Regularization in the selection of basis function centers. Neural Computation 7(3):606–623, 1995.CrossRefGoogle Scholar
  13. [13]
    T. Poggio and S. Edelman, A network that learns to recognize three-dimensional objects. Nature, 343:263–266, 1990.CrossRefGoogle Scholar
  14. [14]
    J. Ponce and A. Zisserman and M. Hebert (Eds.), Object Representation in Computer Vision II, ECCV′96 International Workshop, Cambridge, U.K., April 1996, Springer Verlag, LNCS-1144.Google Scholar
  15. [15]
    A. Roy, S. Govil, and R. Miranda. An algorithm to generate radial basis function (RBF)-like nets for classification problems. Neural Networks 8(2):179–201, 1995.CrossRefGoogle Scholar
  16. [16]
    L. Sardo and J. Kittler, Complexity analysis of RBF networks for pattern recognition, In Proceedings of the CVPR′96 pp. 574–579, 1996.Google Scholar
  17. [17]
    M. Stricker and A. Leonardis. Figure ground segmentation using tabu search. In Proceedings of the IEEE Int. Symposium on Computer Vision Coral Gables, Florida, November 1995.Google Scholar
  18. [18]
    S. Ullman and R. Basri, Recognition by linear combination of models, IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(10):992–1005, October 1991.CrossRefGoogle Scholar
  19. [19]
    T. Werner, R. D. Hersch, and V. Hlaváč, Rendering real-world objects using view interpolation. In Proceedings of the ICCV′95, pp. 957–962, Boston, USA, June 1995. IEEE Press.Google Scholar

Copyright information

© Springer-Verlag Wien 1999

Authors and Affiliations

  • Horst Bischof
    • 1
  • Aleš Leonardis
    • 2
  1. 1.PRIPVienna University of TechnologyViennaAustria
  2. 2.Faculty of Computer and Info. ScienceUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations