Visual and semantic similarity in ImageNet

T. Deselaers, V. Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Many computer vision approaches take for granted positive answers to questions such as “Are semantic categories visually separable?” and “Is visual similarity correlated to semantic similarity?”. In this paper, we study experimentally whether these assumptions hold and show parallels to questions investigated in cognitive science about the human visual system. The insights gained from our analysis enable building a novel distance function between images assessing whether they are from the same basic-level category. This function goes beyond direct visual distance as it also exploits semantic similarity measured through ImageNet. We demonstrate experimentally that it outperforms purely visual distances.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Pages1777-1784
Number of pages8
DOIs
Publication statusPublished - 1 Jun 2011

Keywords

  • cognition
  • computer vision
  • image matching
  • visual databases
  • ImageNet
  • basic-level category
  • cognitive science
  • computer vision approach
  • direct visual distance
  • human visual system
  • semantic category
  • semantic similarity
  • visual similarity
  • Animals
  • Computer vision
  • Histograms
  • Humans
  • Prototypes
  • Semantics
  • Visualization

Fingerprint

Dive into the research topics of 'Visual and semantic similarity in ImageNet'. Together they form a unique fingerprint.

Cite this