Learning Aspect Graph Representations from View Sequences

Abstract

In our effort to develop a modular neural system for invariant learning and recognition of 3D objects, we introduce here a new module architecture called an aspect network constructed around adaptive axo-axo-dendritic synapses. This builds upon our existing system (Seibert & Waxman, 1989) which processes 20 shapes and classifies them into view categories (i.e., aspects) invariant to illumination, position, orientation, scale, and projective deformations. From a sequence of views, the aspect network learns the transitions between these aspects, crystallizing a graph-like structure from an initially amorphous network. Object recognition emerges by accumulating evidence over multiple views which activate competing object hypotheses.