Fragment-Based Learning of Visual Object Categories

Jay Hegdé, Evgeniy Bart, Daniel Kersten

Research output: Contribution to journalArticle

17 Scopus citations

Abstract

When we perceive a visual object, we implicitly or explicitly associate it with a category we know [1-3]. It is known that the visual system can use local, informative image fragments of a given object, rather than the whole object, to classify it into a familiar category [4-8]. How we acquire informative fragments has remained unclear. Here, we show that human observers acquire informative fragments during the initial learning of categories. We created new, but naturalistic, classes of visual objects by using a novel "virtual phylogenesis" (VP) algorithm that simulates key aspects of how biological categories evolve. Subjects were trained to distinguish two of these classes by using whole exemplar objects, not fragments. We hypothesized that if the visual system learns informative object fragments during category learning, then subjects must be able to perform the newly learned categorization by using only the fragments as opposed to whole objects. We found that subjects were able to successfully perform the classification task by using each of the informative fragments by itself, but not by using any of the comparable, but uninformative, fragments. Our results not only reveal that novel categories can be learned by discovering informative fragments but also introduce and illustrate the use of VP as a versatile tool for category-learning research.

Original languageEnglish (US)
Pages (from-to)597-601
Number of pages5
JournalCurrent Biology
Volume18
Issue number8
DOIs
StatePublished - Apr 22 2008
Externally publishedYes

Keywords

  • SYSNEURO

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Fingerprint Dive into the research topics of 'Fragment-Based Learning of Visual Object Categories'. Together they form a unique fingerprint.

  • Cite this