Learning Generative Models via Discriminative Approaches

Authors

  • Mrs.Padma Bhargavi Associate Professor, Department of ECE, Mallareddy Institute of Engineering and Technology, Maisammaguda, Secundrabad Author
  • Mr.P SHEKER Assistant Professor, Department of ECE, St.Martin’s Engineering College, Dulapally, Secundrabad Author
  • Mrs.Jansi Atluri Assistant Professor, Department of ECE, Mallareddy College of Engineering for Women, Maisammaguda, Secudrabad Author

Abstract

Generative model learning is one of the key problems in machine learning and computer vision. Currently the use of generative models is limited due to the difficulty in effectively learning them. A new learning framework is proposed in this paper which progressively learns a target generative distribution through discriminative approaches. This framework provides many interesting aspects to the literature. From the generative model side: (1) A reference distribution is used to assist the learning process, which
removes the need for a samplingprocesses in the early stages. (2) The classification power of discriminative approaches, e.g. boosting, is directly utilized. (3) The ability to select/explore features from a large candidate pool allows us to make nearly no assumptions about the training data. From the discriminative model side: (1) This framework improves the modeling capability of discriminative models. (2) It can start with source training data only and gradually “invent” negative samples. (3) We show how sampling schemes can be introduced to discriminative mod- els. (4) The learning procedure helps to tighten the decision for classification, and therefore, improves robustness. In this paper, we show a variety of applications including texture modeling and classification, non-photo-
realistic rendering, learning image statistics/denoising, and face modeling. The framework handles both homogeneous patterns, e.g. textures, and inhomogeneous patterns, e.g., with nearly an identical parameter setting for all the tasks in the learning stage.

References

Y. Abramson and Y. Freund, “Active Learning for Visual Object Recognition”, UCSD Report, 2006. 1

M. A. Carreira-Perpignan and G. E. Hinton, “On Contrastive Divergence Learning”, Artificial Intelligence and Statistics, Barbados, 2005. 2

S. Della-Pietra and V. Della-Pietra, and J. Lafferty, “Inducing Features of Random Fileds”, IEEE Trans. on PAMI, vol.19, no. 4, April, 1997. 1, 2, 3 (d) (e)

R. Duda, P. Hart, and D. Stork, Pattern Classification and Scene Analysis, second edition, ohn Wiley & Sons, 2000. 1

P. J. Phillips, H. Wechsler, J. Huang, and P. Rauss, “The FERET database and evaluation procedure for face recognition algorithms”, Image and Vision Computing J, vol. 16, no. 5, 1998. 7

Y. Freund and R. Schapire, “A Decision-theoretic Generalization of On-line Learning And An Application to Boosting”, J. of Comp. and Sys. Sci., 55(1), 1997. 1, 3, 6

J. Friedman, T. Hastie and R. Tibshirani, “Additive logistic regression: a statistical view of boosting”, Dept. of Stat., Stanford U. Te. Rep. 1998. 3, 5, 6

S. Geman and D. Geman, “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images,” IEEE Trans. PAMI, vol. 6, pp. 721-741, Nov. 1984. 5

U. Grenander, Y. Chow, and D.Keenan. HANDS: A pattern theoretic study of biological shapes. Springer-Verlag, 1990. 1

A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless, D. H. Salesin, “Image Analogies”, Proc. of SIGGRAPH, Los Angeles, Aug., 2001. 6, 7

G. Hinton, “Training products of experts by minimizing contrastive divergence”, Neural Comp., 14(7): 1771-1800, 2002. 1, 2, 3

A. Hyvarinen, J. Karhunen, E. Oja, “Independent Component Analysis”, John Wiley and Sons, 2001. 1

S. Kumar and M. Hebert, “Discriminative Random Fields: A Discriminative Framework for Contextual Interaction in Classification”, Proc. of ICCV, 2003. 2

J A Lasserre, C M Bishop, T P Minka, “Principled Hybrids of Generative and Discriminative Models”,Proc. of CVPR, 2006. 2

Y. LeCun, “A Tutorial on Energy-Based Learning”,Predicting Strutured Data, MIT Press 2006) 2

L. M. Manevitz and M. Yousef, “One-class SVMs for Document Classification”, J. of Mach. Learn. Res., vol.2, March, 2002. 1

J.S. Liu, Monte Carlo strategies in scientific computing, Springer-Verlag NY INC. 2001. 2, 4, 5

D. Martin, C. Fowlkes, D. Tal, and J. Malik, “A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics,” Proc. ICCV, vol. 2, pp. 416-423, 2001. 6, 7

S. Roth and M. J. Black, “Fields of experts: a framework for learning image priors”, Proc. of CVPR, 2005. 2, 7, 8

M. Turk and A. Pentland, “Face recognition using eigenfaces,” Proc. CVPR, Hawaii, 1991. 1

S. C. Zhu, Y.N. Wu and D.B. Mumford, “Minimax Entropy Principle and Its Applications to Texture Modelin”, Neural Computation Vol. 9, no 8, pp 1627- 1660, Nov. 1997. 1, 2, 3, 6

P. Viola and M. Jones, “Fast Multi-view Face Detection”, Proc. of CVPR, 2001. 5, 6, 7

Y. N. Wu, S. C. Zhu and X. W. Liu, “Equivalence of Julesz Ensemble and FRAME models”, Int’l J. of Comp. Vis. 38(3), 247-265, July, 2000 1

V. Vapnik, “Statistical Learning Theory”. Wiley-Interscience, 1998. 1

M. Welling, G. Hinton, and S. Osindero, “Learning Sparse Topographic Representations with Products of Student-t Distributions”, NIPS, 2002. 2

M. Welling, R. Zemel, G. Hinton, “Self-Supervised Boosting”, NIPS, 2002. 2

Downloads

Published

2026-05-12