Constructing Category Hierarchies for Visual Recognition

Marcin Marszałek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Class hierarchies are commonly used to reduce the complexity of the classification problem. This is crucial in situations when one has to deal with multiple categories. In this work, we evaluate the suitability of class hierarchies currently constructed for visual recognition. We show that top-down as well as bottom-up approaches that are commonly used to automatically construct hierarchies, incorporate assumptions about separability of classes that cannot be fulfilled in the case of visual recognition of a large number of object categories. We propose a modification which is appropriate for most top-down approaches. It allows to construct better class hierarchies that postpone decisions in the presence of uncertainty and thus provide higher recognition accuracy. We also compare our method to flat one-against-all approach and show how to control the speed-for-accuracy trade-off by using our method. For the experimental evaluation, we use the Caltech-256 visual object classes dataset and compare to the state-of-the-art.
Document type :
Conference papers
Liste complète des métadonnées


https://hal.inria.fr/inria-00548656
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 10:24:36 AM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Document(s) archivé(s) le : Monday, March 21, 2011 - 3:28:37 AM

Identifiers

Collections

Citation

Marcin Marszałek, Cordelia Schmid. Constructing Category Hierarchies for Visual Recognition. ECCV 2008 - 10th European Conference on Computer Vision, Oct 2008, Marseille, France. pp.479-491, ⟨10.1007/978-3-540-88693-8_35⟩. ⟨inria-00548656⟩

Share

Metrics

Record views

426

Files downloads

852