A Biologically-Inspired Top-Down Learning Model Based on Visual Attention

摘要

A biologically-inspired top-down learning model based on visual attention is proposed in this paper. Low-level visual features are extracted from learning object itself and do not depend on the background information. All the features are expressed as a feature vector, which is looked as a random variable following a normal distribution. So every learning object is represented as the mean and standard deviation. All the learning objects are combined as an object class, which is represented as classȁ9;s mean and classȁ9;s standard deviation stored in long-term memory (LTM). Then the learned knowledge is used to find the similar location in an attended image. Experimental results indicate that: when the attended object doesnȁ9;t always appear in the background similar to that in the learning objects or their combinations change hugely between learning images and attended images, our model is excellent to the top-down approach of VOCUS and NavaIPakkamȁ9;s statistical model.