PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On sparsity and overcompleteness in image models.
Pietro Berkes, Richard Turner and Maneesh Sahani
In: Advances in Neural Information Processing Systems (2008) MIT Press , Cambridge, USA .

Abstract

Computational models of visual cortex, and in particular those based on sparse coding, have enjoyed much recent attention. Despite this currency, the question of how sparse or how over-complete a sparse representation should be, has gone without principled answer. Here, we use Bayesian model-selection methods to address these questions for a sparse-coding model based on a Student-t prior. Having validated our methods on toy data, we find that natural images are indeed best modelled by extremely sparse distributions; although for the Student-t prior, the associated optimal basis size is only modestly over-complete.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:5246
Deposited By:Maneesh Sahani
Deposited On:24 March 2009