September 2015
Volume 15, Issue 12
Free
Vision Sciences Society Annual Meeting Abstract  |   September 2015
The emergence of decision boundaries is predicted by second order statistics of stimuli in visual categorization
Author Affiliations
  • Feryal M. P. Behbahani
    Dept. of Computing, Imperial College London, UK
  • A. Aldo Faisal
    Dept. of Computing, Imperial College London, UK Dept. of Bioengineering, Imperial College London, UK
Journal of Vision September 2015, Vol.15, 1173. doi:https://doi.org/10.1167/15.12.1173
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Feryal M. P. Behbahani, A. Aldo Faisal; The emergence of decision boundaries is predicted by second order statistics of stimuli in visual categorization. Journal of Vision 2015;15(12):1173. https://doi.org/10.1167/15.12.1173.

      Download citation file:


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

      ×
  • Supplements
Abstract

Categorization is a fundamental and innate ability of our brain, however, its underlying mechanism is not well understood. Previous experimental work on human categorization shows data that is consistent with both discriminative and generative (typically Bayesian) classification. However, the experimental designs used were not able to deliver a test that unambiguously accepts one method while simultaneously rejecting the other. Therefore, we designed a novel experiment in which subjects are trained to distinguish two classes A and B of visual objects, while exemplars of each class are drawn from Gaussian parameter distributions, with equal variance and different means. During the experiment, we test how the subject's representation of the categories changes as a result of being exposed to outliers for only one of the categories, A, far from category B (i.e. increasing category A’s variance). Generative classifiers are by necessity sensitive to novel information becoming available during training, which updates beliefs regarding the generating distribution of each class and assumes class A's variance has increased significantly, thereby reaching across the region occupied by B which predicts an emergence of a new boundary. In contrast, discriminative classifiers are sensitive to novel information only if it affects the immediate discrimination of classes. We observe that, initially, when both categories have equal variance, subjects' decision boundary lies between the two categories consistent with both discriminative and generative algorithms. However, the introduction of the outliers for category A, influences the subject's knowledge of the distribution associated with alternative categories such that objects closer to category B and farthest from category A's outliers will be classified as belonging to category A and thus a new boundary emerges, only predicted by our simulations of generative classifiers. These results give evidence that visual categorization is only consistent with generative and not discriminative classification mechanisms.

Meeting abstract presented at VSS 2015

×
×

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.

×