Selective Attention in the Learning of Invariant Representation of Objects

Abstract

Selective attention plays an important role in visual processing in reducing the problem scale and in actively gathering useful information. We propose a modified saliency map mechanism that uses a simple top-down taskdependent cue to allow attention to stay mainly on one object in the scene each time for the first few shifts. Such a modification allows the learning of invariant object representations across attention shifts in a multiple-object scene. In this paper, we will first introduce this saliency map mechanism and then propose a neural network model to learn invariant representations for objects across attention shifts in a temporal sequence.