Learning by Integrating Information Within and Across Fixations

In this work we present a biologically inspired algorithm for learning object categories that uses Bayesian inference to integrate information within and across fixations. In our model, an object is represented as a collection of features of specific classes arranged at specific locations with respect to the location of the fixation point. Even though the number of feature detectors that we use is large, we show that learning does not require a large amount of training examples due to the fact that between an object and features we introduce an intermediate representation, object views, and thus reduce the dependence among the feature detectors. We tested the system on four object categories and demonstrated that the system can learn a new category from only a few training