A Model for Learning Variance Components of Natural Images
Abstract
We present a hierarchical Bayesian model for learning efficient codes of higher-order structure in natural images. The model, a non-linear gen- eralization of independent component analysis, replaces the standard as- sumption of independence for the joint distribution of coefficients with a distribution that is adapted to the variance structure of the coefficients of an efficient image basis. This offers a novel description of higher- order image structure and provides a way to learn coarse-coded, sparse- distributed representations of abstract image properties such as object location, scale, and texture.
Cite
Text
Karklin and Lewicki. "A Model for Learning Variance Components of Natural Images." Neural Information Processing Systems, 2002.Markdown
[Karklin and Lewicki. "A Model for Learning Variance Components of Natural Images." Neural Information Processing Systems, 2002.](https://mlanthology.org/neurips/2002/karklin2002neurips-model/)BibTeX
@inproceedings{karklin2002neurips-model,
title = {{A Model for Learning Variance Components of Natural Images}},
author = {Karklin, Yan and Lewicki, Michael S.},
booktitle = {Neural Information Processing Systems},
year = {2002},
pages = {1391-1398},
url = {https://mlanthology.org/neurips/2002/karklin2002neurips-model/}
}