October 2003
Volume 3, Issue 9
Vision Sciences Society Annual Meeting Abstract  |   October 2003
Object concept learning from non-normalized data
Author Affiliations
  • Jake V Bouvrie
    Dept. of Brain & Cognitive Sciences, Massachusetts Institute of Technology, USA
Journal of Vision October 2003, Vol.3, 673. doi:10.1167/3.9.673
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Jake V Bouvrie, Pawan Sinha; Object concept learning from non-normalized data. Journal of Vision 2003;3(9):673. doi: 10.1167/3.9.673.

      Download citation file:

      © 2016 Association for Research in Vision and Ophthalmology.

  • Supplements

How does the human visual system learn object concepts from a series of example images? This is a difficult computational challenge given that natural images are often complex and contain many attributes that are irrelevant to the concept that needs to be extracted. Typical computational schemes for concept learning require that the system be provided with a training set of images showing the target object isolated and normalized in location and scale. While such a “pre-processed” training set simplifies the problem, it also renders the approaches unrealistic and circular, because in order to normalize an image, one needs already to possess the object concept.

To address these issues, we propose a computational model for visual object concept learning, motivated by experimental studies of object perception in infancy as well as following recovery from blindness. The model is designed to work with non-normalized training data: Given a set of images, each of which contains an object instance embedded in a complex scene, the system attempts to infer what the object concept is. More specifically, the model uses an unsupervised learning strategy at the outset to formulate hypotheses about possible concepts. At this stage, the processing is, of necessity, bottom-up. The only means of complexity reduction are low-level image saliencies and a priori regularity within an object class. As visual experience accumulates, however, the object concept undergoes concurrent refinement, allowing the model to employ a top-down strategy in an effort to reduce search complexity in subsequent images. Such a mixture of bottom-up and top-down modalities represents a plausible computational analogue to the gradual use of prototypes in object recognition as observed experimentally in humans.

Bouvrie, J. V., Sinha, P.(2003). Object concept learning from non-normalized data [Abstract]. Journal of Vision, 3( 9): 673, 673a, http://journalofvision.org/3/9/673/, doi:10.1167/3.9.673. [CrossRef]

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.