TY - JOUR
T1 - Deep models of superficial face judgments
AU - Peterson, Joshua C.
AU - Uddenberg, Stefan
AU - Griffiths, Thomas L.
AU - Todorov, Alexander
AU - Suchow, Jordan W.
N1 - Publisher Copyright:
Copyright © 2022 the Author(s). Published by PNAS. This open access article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND).
PY - 2022/4/26
Y1 - 2022/4/26
N2 - The diversity of human faces and the contexts in which they appear gives rise to an expansive stimulus space over which people infer psychological traits (e.g., trustworthiness or alertness) and other attributes (e.g., age or adiposity). Machine learning methods, in particular deep neural networks, provide expressive feature representations of face stimuli, but the correspondence between these representations and various human attribute inferences is difficult to determine because the former are high-dimensional vectors produced via black-box optimization algorithms. Here we combine deep generative image models with over 1 million judgments to model inferences of more than 30 attributes over a comprehensive latent face space. The predictive accuracy of our model approaches human interrater reliability, which simulations suggest would not have been possible with fewer faces, fewer judgments, or lower-dimensional feature representations. Our model can be used to predict and manipulate inferences with respect to arbitrary face photographs or to generate synthetic photorealistic face stimuli that evoke impressions tuned along the modeled attributes.
AB - The diversity of human faces and the contexts in which they appear gives rise to an expansive stimulus space over which people infer psychological traits (e.g., trustworthiness or alertness) and other attributes (e.g., age or adiposity). Machine learning methods, in particular deep neural networks, provide expressive feature representations of face stimuli, but the correspondence between these representations and various human attribute inferences is difficult to determine because the former are high-dimensional vectors produced via black-box optimization algorithms. Here we combine deep generative image models with over 1 million judgments to model inferences of more than 30 attributes over a comprehensive latent face space. The predictive accuracy of our model approaches human interrater reliability, which simulations suggest would not have been possible with fewer faces, fewer judgments, or lower-dimensional feature representations. Our model can be used to predict and manipulate inferences with respect to arbitrary face photographs or to generate synthetic photorealistic face stimuli that evoke impressions tuned along the modeled attributes.
KW - computational models
KW - face perception
KW - social traits
UR - http://www.scopus.com/inward/record.url?scp=85128638726&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85128638726&partnerID=8YFLogxK
U2 - 10.1073/pnas.2115228119
DO - 10.1073/pnas.2115228119
M3 - Article
C2 - 35446619
AN - SCOPUS:85128638726
SN - 0027-8424
VL - 119
JO - Proceedings of the National Academy of Sciences of the United States of America
JF - Proceedings of the National Academy of Sciences of the United States of America
IS - 17
M1 - e2115228119
ER -