Method and system for optimizing accuracy-specificity trade-offs in large scale visual recognition

US9779291B2 · kind B2 · utility

Assignee

• The Board of Trustees of the Leland Stanford Junior University · US

Inventors

• Fei Li · Pu, CN
• Jia Deng · Mountain View, US
• Jonathan Krause · Marlboro, US
• Alexander Berg · Mannheim, DE

Key dates

• Filing date: Oct 12, 2015
• Grant date: Oct 3, 2017
• Expiry date: Oct 12, 2035

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V40/103
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

As visual recognition scales up to ever larger numbers of categories, maintaining high accuracy is increasingly difficult. Embodiment of the present invention include methods for optimizing accuracy-specificity trade-offs in large scale recognition where object categories form a semantic hierarchy consisting of many levels of abstraction.