A Model for Learning Variance Components of Natural Images
Yan Karklin, Michael S. Lewicki · Neural Information Processing Systems · 2002
We present a hierarchical Bayesian model for learning efficient codes of higher-order structure in natural images. The model, a non-linear generalization of independent component analysis, replaces the standard assumption 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.