September 2018
Volume 18, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   September 2018
Sampling from object and scene representations using deep feature spaces
Author Affiliations
  • Joshua Peterson
    Department of Psychology, University of California, Berkeley
  • Krishan Aghi
    Department of Psychology, University of California, Berkeley
  • Jordan Suchow
    Department of Psychology, University of California, Berkeley
  • Alexander Ku
    Department of Psychology, University of California, Berkeley
  • Thomas Griffiths
    Department of Psychology, University of California, Berkeley
Journal of Vision September 2018, Vol.18, 403. doi:https://doi.org/10.1167/18.10.403
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Joshua Peterson, Krishan Aghi, Jordan Suchow, Alexander Ku, Thomas Griffiths; Sampling from object and scene representations using deep feature spaces. Journal of Vision 2018;18(10):403. https://doi.org/10.1167/18.10.403.

      Download citation file:


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

      ×
  • Supplements
Abstract

Decades of research on how people represent visual categories have yielded a variety of formal theories, but validating them with naturalistic visual stimuli such as objects and scenes remains a challenge. The key problems are that human visual category representations cannot be directly observed and designing informative experiments using rich visual stimuli such as photographs requires having a reasonable representation of these images. Deep neural networks have recently been successful in a range of computer vision tasks and provide a way to represent the features of images. Here we outline a method for estimating the structure of human visual categories that draws on ideas from both cognitive science and machine learning, blending human-based algorithms with state-of-the-art deep representation learners. We provide qualitative and quantitative results as a proof of concept for the feasibility of the method. Samples drawn from human distributions rival the quality of current state-of-the-art generative models and outperform alternative methods for estimating the structure of human categories.

Meeting abstract presented at VSS 2018

×
×

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.

×