A Caltech Library Service

Learning and Using Taxonomies For Fast Visual Categorization

Griffin, Gregory and Perona, Pietro (2008) Learning and Using Taxonomies For Fast Visual Categorization. In: IEEE Conference on Computer Vision and Pattern Recognition, 2008. Proceedings – IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE , pp. 1-8. ISBN 978-1-4244-2242-5.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously N_(cat) = 10^4 - 10^5 visual categories requires sub-linear classification costs. We explore algorithms for automatically building classification trees which have, in principle, log N_(cat) complexity. We find that a greedy algorithm that recursively splits the set of categories into the two minimally confused subsets achieves 5-20 fold speedups at a small cost in classification performance. Our approach is independent of the specific classification algorithm used. A welcome by-product of our algorithm is a very reasonable taxonomy of the Caltech-256 dataset.

Item Type:Book Section
Related URLs:
URLURL TypeDescription*%26searchField%3DSearch+AllPublisherUNSPECIFIED
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2009 IEEE. Issue Date : 23-28 June 2008; Date of Current Version : 05 August 2008. Research funded by National Science Foundation grant NSF IIS-0535292 and by ONR MURI grant N00014-06- 0734.
Funding AgencyGrant Number
NSFNSF IIS-0535292
Office of Naval Research Multidisciplinary University Research Initiative (ONR MURI)N00014-06-0734
Other Numbering System:
Other Numbering System NameOther Numbering System ID
INSPEC Accession Number10139715
Series Name:Proceedings – IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Record Number:CaltechAUTHORS:20100623-113346775
Persistent URL:
Official Citation:Griffin, G.; Perona, P.; , "Learning and using taxonomies for fast visual categorization," Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on , vol., no., pp.1-8, 23-28 June 2008 doi: 10.1109/CVPR.2008.4587410 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:18774
Deposited On:25 Jun 2010 20:53
Last Modified:08 Nov 2021 23:46

Repository Staff Only: item control page