Chapter

Computer Vision – ECCV 2008

Volume 5305 of the series Lecture Notes in Computer Science pp 479-491

Constructing Category Hierarchies for Visual Recognition

  • Marcin MarszałekAffiliated withINRIA Grenoble, LEAR, LJK
  • , Cordelia SchmidAffiliated withINRIA Grenoble, LEAR, LJK

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Class hierarchies are commonly used to reduce the complexity of the classification problem. This is crucial when dealing with a large number of categories. In this work, we evaluate class hierarchies currently constructed for visual recognition. We show that top-down as well as bottom-up approaches, which are commonly used to automatically construct hierarchies, incorporate assumptions about the separability of classes. Those assumptions do not hold for visual recognition of a large number of object categories. We therefore propose a modification which is appropriate for most top-down approaches. It allows to construct class hierarchies that postpone decisions in the presence of uncertainty and thus provide higher recognition accuracy. We also compare our method to a one-against-all approach and show how to control the speed-for-accuracy trade-off with our method. For the experimental evaluation, we use the Caltech-256 visual object classes dataset and compare to state-of-the-art methods.