Unsupervised Neural Architecture for Saliency Detection: Extended Version

TL;DR

This paper introduces an unsupervised neural network model inspired by neurophysiology for visual saliency detection, utilizing PCA and Hebbian learning to simulate human attention mechanisms, validated through psychological experiments.

Contribution

The paper presents a novel neurophysiologically inspired neural architecture for saliency detection that employs PCA and Hebbian learning, with experimental validation.

Findings

Model achieves good performance in saliency detection

Simulation results align with psychological experiment outcomes

Utilizes biologically plausible mechanisms for feature extraction

Abstract

We propose a novel neural network architecture for visual saliency detections, which utilizes neurophysiologically plausible mechanisms for extraction of salient regions. The model has been significantly inspired by recent findings from neurophysiology and aimed to simulate the bottom-up processes of human selective attention. Two types of features were analyzed: color and direction of maximum variance. The mechanism we employ for processing those features is PCA, implemented by means of normalized Hebbian learning and the waves of spikes. To evaluate performance of our model we have conducted psychological experiment. Comparison of simulation results with those of experiment indicates good performance of our model.