September 2017
Volume 17, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   August 2017
Similarities Between Deep Neural Networks and Brain Regions In Processing Good and Bad Exemplars of Natural Scenes
Author Affiliations
  • Manoj Kumar
    Neuroscience Program, University of Illinois at Urbana-Champaign
    Beckman Institute, University of Illinois at Urbana-Champaign
  • Shuchen Zhang
    Department of Computer Engineering, University of Illinois at Urbana-Champaign
  • Diane Beck
    Neuroscience Program, University of Illinois at Urbana-Champaign
    Beckman Institute, University of Illinois at Urbana-Champaign
Journal of Vision August 2017, Vol.17, 297. doi:10.1167/17.10.297
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Manoj Kumar, Shuchen Zhang, Diane Beck; Similarities Between Deep Neural Networks and Brain Regions In Processing Good and Bad Exemplars of Natural Scenes. Journal of Vision 2017;17(10):297. doi: 10.1167/17.10.297.

      Download citation file:


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

      ×
  • Supplements
Abstract

The layers of Deep Neural Networks (DNNs) have shown some commonality with processing in the visual cortical hierarchy. It is unclear, however, whether DNNs capture other behavioral regularities of natural scenes, e.g. the representativeness of an image to its category. Humans are better at categorizing and detecting good (more representative of category) than bad exemplars of natural scenes. Similarly, prior work has shown that good exemplars are decoded better than bad exemplars in V1 as well as higher visual areas such as the retrosplenial cortex (RSC) and the parahippocampal place area (PPA). Here we ask whether a DNN, that was not explicitly informed about representativeness of its training set, shows a similar good exemplar advantage, and if so in which layers do we see this effect. We used good and bad exemplars from six categories of natural scenes (beaches, city streets, forests, highways, mountains and offices) and processed them through the pre-trained Places205-AlexNet. We asked both whether this DNN could distinguish good from bad scenes, as well as whether 6-way category classification differed for good and bad exemplars. Classification was performed using the feature space of each layer separately. Our results show that while in the lowest layer (conv1) there is insufficient information to make a good vs. bad discrimination, the layer (fc7) (the second highest fully connected layer) can clearly make this discrimination. Furthermore, the six-way categorization was better for good exemplars than bad exemplars in lower and higher layers, although categorization accuracy increases overall at the higher layers. This parallels results seen in V1, RSC and PPA, and suggests that the DNN learns statistical regularities that distinguish good from bad exemplars without such information being explicitly encoded into the training set.

Meeting abstract presented at VSS 2017

×
×

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.

×