August 2023
Volume 23, Issue 9
Open Access
Vision Sciences Society Annual Meeting Abstract  |   August 2023
Using deep neural networks to test possible origins of human face perception
Author Affiliations
  • Katharina Dobs
    Justus-Liebig University Giessen
Journal of Vision August 2023, Vol.23, 4678. doi:https://doi.org/10.1167/jov.23.9.4678
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Katharina Dobs; Using deep neural networks to test possible origins of human face perception. Journal of Vision 2023;23(9):4678. https://doi.org/10.1167/jov.23.9.4678.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Human face recognition is highly accurate, and exhibits a number of distinctive and well documented behavioral and neural "signatures" such as the face-inversion effect, the other-race effect and neural specialization for faces. How does the remarkable human ability of face recognition arise in development? Is experience with faces required, and if so, what kind of experience? We cannot straightforwardly manipulate visual experience during development in humans, but we can ask what is possible in machines. Here, I will present our work testing whether convolutional neural networks (CNNs) optimized on different tasks with varying visual experience capture key aspects of human face perception. We find that only face-trained – not object-trained or untrained – CNNs achieved human-level performance on face recognition and exhibited behavioral signatures of human face perception. Moreover, these signatures emerged only in CNNs trained for face identification, not in CNNs that were matched in the amount of face experience but trained on a face detection task. Critically, similar to human visual cortex, CNNs trained on both face and object recognition spontaneously segregated themselves into distinct subsystems for each. These results indicate that humanlike face perception abilities and neural characteristics emerge in machines and could in principle arise in humans (through development or evolution or both) after extensive training on real-world face recognition without face-specific predispositions, but that experience with objects alone is not sufficient. I will conclude by discussing how this computational approach offers novel ways to illuminate how and why visual recognition works the way it does.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×