December 2022
Volume 22, Issue 14
Open Access
Vision Sciences Society Annual Meeting Abstract  |   December 2022
Are Machines more Effective than Humans for Graphical Perception Tasks?
Author Affiliations
  • Shuning Jiang
    The Ohio State University
  • Wei-Lun Chao
    The Ohio State University
  • Jian Chen
    The Ohio State University
  • Daniel Haehn
    University of Massachusetts Boston
  • Meng Ling
    The Ohio State University
  • Ce Shang
    The Ohio State University
  • Hanspeter Pfister
    Harvard University
Journal of Vision December 2022, Vol.22, 3784. doi:https://doi.org/10.1167/jov.22.14.3784
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Shuning Jiang, Wei-Lun Chao, Jian Chen, Daniel Haehn, Meng Ling, Ce Shang, Hanspeter Pfister; Are Machines more Effective than Humans for Graphical Perception Tasks?. Journal of Vision 2022;22(14):3784. https://doi.org/10.1167/jov.22.14.3784.

      Download citation file:


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

      ×
  • Supplements
Abstract

Position and length are two dominant visual channels that underpin our ability to reason about the visual world in settings ranging from natural scenes to charts and diagrams. Despite progress in convolutional neural networks (CNNs) performing image classification, we know little about cognitive tasks where models need to understand the relationships between objects in charts. When asked, "What is the ratio between two bars?" CNNs will need to identify the bars in an image and the relationship between bars to answer correctly. In this work, we answer questions about how well can a CNN cope with new images after it has learned from a particular set of ratios or heights that were distorted to further away from each other or shifted to never seen before? Are machines more effective than humans for ratio estimate tasks? In two experiments, we sent the models to take the same human tests to compare these two experts. We controlled four train-test configurations to be the same or carry distribution shifted on two features: (1) task label (ratios) and (2) visual feature (bar heights). We found that sampling methods lowered the human errors up to three-folds when we aggregated the predictions. However, CNNs were not robust to distribution shift: accuracy dropped significantly when specific test instances fell out of the training data span. Next, we introduce a trial-by-trial comparison to measure if the two experts systematically make errors of the same inputs. We found that, unlike humans, CNNs were remarkably consistent with one another and showed marginal position preferences over length. We further test for the presence of Weber's law in CNNs and humans by selecting bar heights such that the height difference computed on pairs of images spanned a wide range. We observed the presence of Weber's law for neither CNNs nor humans.

×
×

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.

×