Bootstrapped learning of novel objects

Mark J. Brady, Daniel J Kersten

Research output: Contribution to journalArticle

42 Scopus citations

Abstract

Recognition of familiar objects in cluttered backgrounds is a challenging computational problem. Camouflage provides a particularly striking case, where an object is difficult to detect, recognize, and segment even when in "plain view." Current computational approaches combine low-level features with high-level models to recognize objects. But what if the object is unfamiliar? A novel camouflaged object poses a paradox: A visual system would seem to require a model of an object's shape in order to detect, recognize, and segment it when camouflaged. But, how is the visual system to build such a model of the object without easily segmentable samples? One possibility is that learning to identify and segment is opportunistic in the sense that learning of novel objects takes place only when distinctive clues permit object segmentation from background, such as when target color or motion enables segmentation on single presentations. We tested this idea and discovered that, on the contrary, human observers can learn to identify and segment a novel target shape, even when for any given training image the target object is camouflaged. Further, perfect recognition can be achieved without accurate segmentation. We call the ability to build a shape model from high-ambiguity presentations bootstrapped learning.

Original languageEnglish (US)
Pages (from-to)413-422
Number of pages10
JournalJournal of vision
Volume3
Issue number6
DOIs
StatePublished - Jul 22 2003

Keywords

  • Background
  • Bottom up
  • Camouflage
  • Clutter
  • Color
  • Learning
  • Mechanochemical
  • Morphogenesis
  • Motion
  • Novel objects
  • Object recognition
  • Segmentation
  • Top down

Fingerprint Dive into the research topics of 'Bootstrapped learning of novel objects'. Together they form a unique fingerprint.

  • Cite this