A Model for Learning Variance Components of Natural Images

@inproceedings{Karklin2002AMF,
  title={A Model for Learning Variance Components of Natural Images},
  author={Yan Karklin and Michael S. Lewicki},
  booktitle={NIPS},
  year={2002}
}
We present a hierarchical Bayesian model for learning effici nt codes of higher-order structure in natural images. The model, a nonlinear generalization of independent component analysis, replaces t he tandard assumption of independence for the joint distribution of coef ficients with a distribution that is adapted to the variance structure of t he coefficients of an efficient image basis. This offers a novel description o f higherorder image structure and provides a way to learn coarse-cod d… CONTINUE READING

Similar Papers

Loading similar papers…