A Neural Network Model of Spatial and Feature-Based Attention

TL;DR

This paper presents a neural network model that mimics human visual attention, demonstrating emergent spatial and feature-based attention patterns that align with human cognition, offering insights into visual processing.

Contribution

The model uniquely combines two networks to simulate top-down attention mechanisms, revealing emergent attention patterns comparable to human visual attention.

Findings

Emergent spatial and feature-based attention patterns in the model

Model's attention responses resemble human visual attention

Potential for studying human cognition through neural networks

Abstract

Visual attention is a mechanism closely intertwined with vision and memory. Top-down information influences visual processing through attention. We designed a neural network model inspired by aspects of human visual attention. This model consists of two networks: one serves as a basic processor performing a simple task, while the other processes contextual information and guides the first network through attention to adapt to more complex tasks. After training the model and visualizing the learned attention response, we discovered that the model's emergent attention patterns corresponded to spatial and feature-based attention. This similarity between human visual attention and attention in computer vision suggests a promising direction for studying human cognition using neural network models.