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

## Author(s): Deng, Jia; Krause, Jonathan; Berg, Alexander C; Li, Fei-Fei

To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1pz4w
DC FieldValueLanguage
dc.contributor.authorDeng, Jia-
dc.contributor.authorKrause, Jonathan-
dc.contributor.authorBerg, Alexander C-
dc.contributor.authorLi, Fei-Fei-
dc.date.accessioned2021-10-08T19:45:47Z-
dc.date.available2021-10-08T19:45:47Z-
dc.date.issued2012en_US
dc.identifier.citationDeng, Jia, Jonathan Krause, Alexander C. Berg, and Li Fei-Fei. "Hedging your bets: Optimizing accuracy-specificity trade-offs in large scale visual recognition." IEEE Conference on Computer Vision and Pattern Recognition (2012): pp. 3450-3457. doi:10.1109/CVPR.2012.6248086en_US
dc.identifier.issn1063-6919-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1pz4w-
dc.description.abstractAs 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.en_US
dc.format.extent3450 - 3457en_US
dc.language.isoen_USen_US
dc.relation.ispartofIEEE Conference on Computer Vision and Pattern Recognitionen_US
dc.rightsAuthor's manuscripten_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/CVPR.2012.6248086-
dc.identifier.eissn1063-6919-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat