Sciweavers

CVPR
2008
IEEE

Learning and using taxonomies for fast visual categorization

14 years 5 months ago
Learning and using taxonomies for fast visual categorization
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104 - 105 visual categories requires sub-linear classification costs. We explore algorithms for automatically building classification trees which have, in principle, log Ncat 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 byproduct of our algorithm is a very reasonable taxonomy of the Caltech-256 dataset.
Gregory Griffin, Darya Perona
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Gregory Griffin, Darya Perona
Comments (0)