Introducing Memory and Association Mechanism into a Biologically Inspired Visual Model

TL;DR

This paper enhances a biologically inspired hierarchical visual model by integrating memory and association mechanisms, enabling more efficient object recognition with reduced memory usage and added top-down adjustments.

Contribution

It introduces memory and association mechanisms into an existing hierarchical model, improving efficiency and biological plausibility for visual recognition tasks.

Findings

Achieves position- and scale-tolerant recognition

Reduces memory requirements significantly

Maintains high recognition performance

Abstract

A famous biologically inspired hierarchical model firstly proposed by Riesenhuber and Poggio has been successfully applied to multiple visual recognition tasks. The model is able to achieve a set of position- and scale-tolerant recognition, which is a central problem in pattern recognition. In this paper, based on some other biological experimental results, we introduce the Memory and Association Mechanisms into the above biologically inspired model. The main motivations of the work are (a) to mimic the active memory and association mechanism and add the 'top down' adjustment to the above biologically inspired hierarchical model and (b) to build up an algorithm which can save the space and keep a good recognition performance. The new model is also applied to object recognition processes. The primary experimental results show that our method is efficient with much less memory requirement.