Learning generative texture models with extended Fields-of-Experts
Nicolas Heess, Christopher Williams and Geoffrey Hinton
In: Brtish Machine Vision Conference 2009, 7-10 Sept 2009, London, UK.
We evaluate the ability of the popular Field-of-Experts (FoE) to model structure in
images. As a test case we focus on modeling synthetic and natural textures. We find
that even for modeling single textures, the FoE provides insufficient flexibility to learn
good generative models it does not perform any better than the much simpler Gaussian
FoE. We propose an extended version of the FoE (allowing for bimodal potentials) and
demonstrate that this novel formulation, when trained with a better approximation of the
likelihood gradient, gives rise to a more powerful generative model of specific visual
structure that produces significantly better results for the texture task.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Christopher Williams|
|Deposited On:||08 March 2010|