CNN-based search model underestimates attention guidance by simple visual features

2021/03/29 by Endel Poder, Poder, Endel
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #Neurons and Cognition (q-bio.NC) #cs.CV #q-bio.NC

paper · pdf · doi:10.48550/arxiv.2103.15439

6 pages, 2 figures

arxiv created 2021/04/25 · arxiv updated 2021/04/27

Abstract

Recently, Zhang et al. (2018) proposed an interesting model of attention guidance that uses visual features learnt by convolutional neural networks for object recognition. I adapted this model for search experiments with accuracy as the measure of performance. Simulation of our previously published feature and conjunction search experiments revealed that CNN-based search model considerably underestimates human attention guidance by simple visual features. A simple explanation is that the model has no bottom-up guidance of attention. Another view might be that standard CNNs do not learn features required for human-like attention guidance.

Related

• Feature-based Attention in Convolutional Neural Networks
• Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity
• Capacity limitations of visual search in deep convolutional neural networks
• Understanding More about Human and Machine Attention in Deep Neural Networks
• A normalization model of visual search predicts single trial human fixations in an object search task