Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition

Jia Deng, Jonathan Krause, Alexander C. Berg, Li Fei-Fei

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

84 Scopus citations

Abstract

As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. In this work, we study the problem of optimizing accuracy-specificity trade-offs in large scale recognition, motivated by the observation that object categories form a semantic hierarchy consisting of many levels of abstraction. A classifier can select the appropriate level, trading off specificity for accuracy in case of uncertainty. By optimizing this trade-off, we obtain classifiers that try to be as specific as possible while guaranteeing an arbitrarily high accuracy. We formulate the problem as maximizing information gain while ensuring a fixed, arbitrarily small error rate with a semantic hierarchy. We propose the Dual Accuracy Reward Trade-off Search (DARTS) algorithm and prove that, under practical conditions, it converges to an optimal solution. Experiments demonstrate the effectiveness of our algorithm on datasets ranging from 65 to over 10,000 categories.

Original languageEnglish (US)
Title of host publication2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Pages3450-3457
Number of pages8
DOIs
StatePublished - Oct 1 2012
Event2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012 - Providence, RI, United States
Duration: Jun 16 2012Jun 21 2012

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
CountryUnited States
CityProvidence, RI
Period6/16/126/21/12

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition'. Together they form a unique fingerprint.

Cite this