Abstract
We propose a new framework for calibrating parameters of energy functionals, as used in image analysis. The method learns parameters from a family of correct examples, and given a probabilistic construct for generating wrong examples from correct ones. We introduce a measure of frustration to penalize cases in which wrong responses are preferred to correct ones, and we design a stochastic gradient algorithm which converges to parameters which minimize this measure of frustration. We also present a first set of experiments in this context, and introduce extensions to deal with data-dependent energies.
Chapter PDF
References
R. Azencott, Image analysis and markov fields, in Proc. of the Int. Conf. on Ind. and Appl. Math, SIAM, Paris, 1987.
A. Benveniste, M. Métivier, AND P. Priouret, Algorithmes Adaptatifs et Approximations Stochastiques, Théorie et Application, Masson, 1987.
S. Geman AND D. Geman, Stochastic relaxation, gibbs distributions, and the bayesian restoration of images, IEEE Trans. PAMI, 6 (1984), pp. 721–741.
J. J. Hopfield, iNeural networks and physical systems with emergent collective computational abilities, Proc. Nat. Acad. Sci USA, 79 (1982), pp. 2554–2558. Biophysics.
D. Mumford and Shah, Optimal approximation by piecewise smooth functions and variational problems, Comm. Pure and Appl. Math., XLII (1988).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Younes, L. (2000). Calibrating Parameters of Cost Functionals. In: Vernon, D. (eds) Computer Vision — ECCV 2000. ECCV 2000. Lecture Notes in Computer Science, vol 1843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45053-X_14
Download citation
DOI: https://doi.org/10.1007/3-540-45053-X_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67686-7
Online ISBN: 978-3-540-45053-5
eBook Packages: Springer Book Archive