Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Zhenhua, Chen, Ji, Lin, Zhicheng, Ying, Haojiang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.18800
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912327424540672
author Zhao, Zhenhua
Chen, Ji
Lin, Zhicheng
Ying, Haojiang
author_facet Zhao, Zhenhua
Chen, Ji
Lin, Zhicheng
Ying, Haojiang
contents Whether face processing depends on unique, domain-specific neurocognitive mechanisms or domain-general object recognition mechanisms has long been debated. Directly testing these competing hypotheses in humans has proven challenging due to extensive exposure to both faces and objects. Here, we systematically test these hypotheses by capitalizing on recent progress in convolutional neural networks (CNNs) that can be trained without face exposure (i.e., pre-trained weights). Domain-general mechanism accounts posit that face processing can emerge from a neural network without specialized pre-training on faces. Consequently, we trained CNNs solely on objects and tested their ability to recognize and represent faces as well as objects that look like faces (face pareidolia stimuli).... Due to the character limits, for more details see in attached pdf
format Preprint
id arxiv_https___arxiv_org_abs_2405_18800
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Face processing emerges from object-trained convolutional neural networks
Zhao, Zhenhua
Chen, Ji
Lin, Zhicheng
Ying, Haojiang
Computer Vision and Pattern Recognition
Whether face processing depends on unique, domain-specific neurocognitive mechanisms or domain-general object recognition mechanisms has long been debated. Directly testing these competing hypotheses in humans has proven challenging due to extensive exposure to both faces and objects. Here, we systematically test these hypotheses by capitalizing on recent progress in convolutional neural networks (CNNs) that can be trained without face exposure (i.e., pre-trained weights). Domain-general mechanism accounts posit that face processing can emerge from a neural network without specialized pre-training on faces. Consequently, we trained CNNs solely on objects and tested their ability to recognize and represent faces as well as objects that look like faces (face pareidolia stimuli).... Due to the character limits, for more details see in attached pdf
title Face processing emerges from object-trained convolutional neural networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.18800