Minimax Entropy and Learning by Diffusion

1 A system of coupled differential equations is formulated which learns priors for modelling "preattentive" textures. It is derived from an energy functional consisting of a linear combination of a large number of terms corresponding to the features that the system is capable of learning. The system learns the parameters associated with each feature by applying gradient ascent to the log-likelihood function. Updates of each parameter are thus governed by the residual with respect to the corresponding feature. A feature residual is computed from its observed value and the value generated by the system. The latter is calculated from a synthesized sample image which is generated by means of a reaction-diffusion equation obtained by applying gradient descent to the energy functional.

• Type: Conference
• Year: 1998
• Where: CVPR
• Authors: Jayant Shah
• Keywords: Computer Vision, CVPR 1998, Energy Functional, Feature Residual, Gradient Ascent