Using drawings and deep neural networks to characterize the building blocks of human visual similarity.

Early in life and without special training, human beings discern resemblance between abstract visual stimuli, such as drawings, and the real-world objects they represent. We used this capacity for visual abstraction as a tool for evaluating deep neural networks (DNNs) as models of human visual perce...

Full description

Bibliographic Details

Published in:	Memory & Cognition Vol. 53; no. 1; pp. 219 - 242
Main Authors:	Mukherjee, Kushin, Rogers, Timothy T.
Format:	Article
Published:	Springer Nature Jan2025
Subjects:	Task performance Semantics Judgment (Psychology) Statistical models Drawing Statistical sampling Convolutional neural networks Descriptive statistics Deep learning Visual perception Factor analysis Regression analysis
Online Access:	View this record in EBSCOhost