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. https://resolver.caltech.edu/CaltechAUTHORS:20100623-113346775
![]()
|
PDF
- Published Version
See Usage Policy. 987kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20100623-113346775
Abstract
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: | |||||||
ORCID: |
| ||||||
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. | ||||||
Funders: |
| ||||||
Other Numbering System: |
| ||||||
Series Name: | Proceedings – IEEE Computer Society Conference on Computer Vision and Pattern Recognition | ||||||
DOI: | 10.1109/CVPR.2008.4587410 | ||||||
Record Number: | CaltechAUTHORS:20100623-113346775 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20100623-113346775 | ||||||
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: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4587410&isnumber=4587335 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 18774 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | INVALID USER | ||||||
Deposited On: | 25 Jun 2010 20:53 | ||||||
Last Modified: | 08 Nov 2021 23:46 |
Repository Staff Only: item control page