Disrupted visual input unveils the computational details of artificial neural networks for face perception

Convolutional Neural Network (DCNN), with its great performance, has attracted attention of researchers from many disciplines. The studies of the DCNN and that of biological neural systems have inspired each other reciprocally. The brain-inspired neural networks not only achieve great performance bu...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in computational neuroscience 2022-11, Vol.16, p.1054421-1054421
Main Authors: Li, Yi-Fan, Ying, Haojiang
Format: Article
Language:English
Subjects:
Ablation
Artificial intelligence
artificial neural networks (ANN)
cognitive science
computational vision
Computer applications
Ethnicity
Experiments
face perception
Human performance
Neural networks
Neuroscience
Neurosciences
Perception
Performance evaluation
Psychophysics
Quantitative psychology
vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional Neural Network (DCNN), with its great performance, has attracted attention of researchers from many disciplines. The studies of the DCNN and that of biological neural systems have inspired each other reciprocally. The brain-inspired neural networks not only achieve great performance but also serve as a computational model of biological neural systems. Here in this study, we trained and tested several typical DCNNs (AlexNet, VGG11, VGG13, VGG16, DenseNet, MobileNet, and EfficientNet) with a face ethnicity categorization task for experiment 1, and an emotion categorization task for experiment 2. We measured the performance of DCNNs by testing them with original and lossy visual inputs (various kinds of image occlusion) and compared their performance with human participants. Moreover, the class activation map (CAM) method allowed us to visualize the foci of the "attention" of these DCNNs. The results suggested that the VGG13 performed the best: Its performance closely resembled human participants in terms of psychophysics measurements, it utilized similar areas of visual inputs as humans, and it had the most consistent performance with inputs having various kinds of impairments. In general, we examined the processing mechanism of DCNNs using a new paradigm and found that VGG13 might be the most human-like DCNN in this task. This study also highlighted a possible paradigm to study and develop DCNNs using human perception as a benchmark.
ISSN:1662-5188
1662-5188
DOI:10.3389/fncom.2022.1054421