December 2017
Volume 17, Issue 15
Open Access
OSA Fall Vision Meeting Abstract  |   December 2017
Evidence for configural superiority effects in convolutional neural networks
Author Affiliations
  • Shaiyan Keshvari
    CSAIL, MIT
  • Ruth Rosenholtz
    CSAIL, MIT
Journal of Vision December 2017, Vol.17, 44. doi:10.1167/17.15.44
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Shaiyan Keshvari, Ruth Rosenholtz; Evidence for configural superiority effects in convolutional neural networks. Journal of Vision 2017;17(15):44. doi: 10.1167/17.15.44.

      Download citation file:


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

      ×
  • Supplements
Abstract

Finding a left-tilted line among right-tilted becomes easier with an “L” added to each item, transforming the task into one of finding a triangle among arrows. This configural superiority effect occurs for a wide array of stimuli, and is thought to result from vision utilizing “emergent” features (EFs), such as closure, in the composite case. A more computational interpretation can be couched in idea of a visual processing hierarchy, in which higher level representations support complex tasks at the expense of other, possibly less ecologically relevant tasks. Detecting the oddball might be inherently easier in the composite condition given the representation at some level of the hierarchy. To test this, we used the VGG-16 (Simonyan & Zisserman, 2015) convolutional neural network (CNN), trained to recognize objects using the ImageNet dataset, as a standin for the hierarchical visual encoding. Such CNNs have high performance on object recognition, as well as on tasks for which they are not trained. Feature vectors at different layers correlate with responses of various brain areas (Hong et al., 2015). We tested five EF stimuli in a 4AFC oddball localization task (Pomerantz & Cragin, 2013). We trained a multi-class SVM operating on the outputs of the last fully connected layer, and performed a K-fold cross-validation. Two EFs (orthogonality and roundness) show better performance (33 and 53 percentage points, respectively) in the composite than the base case. One (closure) showed no effect (

×
×

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.

×