September 2018
Volume 18, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   September 2018
Comparing the ability of humans and DNNs to recognise closed contours in cluttered images
Author Affiliations
  • Christina Funke
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
  • Judy Borowski
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
  • Thomas Wallis
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
  • Wieland Brendel
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
  • Alexander Ecker
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
  • Matthias Bethge
    Centre for Integrative Neuroscience , Eberhard Karls Universität TübingenBernstein Center for Computational Neuroscience, Tübingen, Germany
Journal of Vision September 2018, Vol.18, 800. doi:10.1167/18.10.800
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Christina Funke, Judy Borowski, Thomas Wallis, Wieland Brendel, Alexander Ecker, Matthias Bethge; Comparing the ability of humans and DNNs to recognise closed contours in cluttered images. Journal of Vision 2018;18(10):800. doi: 10.1167/18.10.800.

      Download citation file:


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

      ×
  • Supplements
Abstract

Given the recent success of machine vision algorithms in solving complex visual inference tasks, it becomes increasingly challenging to find tasks for which machines are still outperformed by humans. We seek to identify such tasks and test them under controlled settings. Here we compare human and machine performance in one candidate task: discriminating closed and open contours. We generated contours using simple lines of varying length and angle, and minimised statistical regularities that could provide cues. It has been shown that DNNs trained for object recognition are very sensitive to texture cues (Gatys et al., 2015). We use this insight to maximize the difficulty of the task for the DNN by adding random natural images to the background. Humans performed a 2IFC task discriminating closed and open contours (100 ms presentation) with and without background images. We trained a readout network to perform the same task using the pre-trained features of the VGG-19 network. With no background image (contours black on grey), humans reach a performance of 92% correct on the task, dropping to 71% when background images are present. Surprisingly, the model's performance is very similar to humans, with 91% dropping to 64% with background. One contributing factor for why human performance drops with background images is that dark lines become difficult to discriminate from the natural images, whose average pixel values are dark. Changing the polarity of the lines from dark to light improved human performance (96% without and 82% with background image) but not model performance (88% without to 64% with background image), indicating that humans could largely ignore the background image whereas the model could not. These results show that the human visual system is able to discriminate closed from open contours in a more robust fashion than transfer learning from the VGG network.

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.

×