Learning and using taxonomies for fast visual categorization
Top Cited Papers
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
- https://doi.org/10.1109/cvpr.2008.4587410
Abstract
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, logNcat 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.Keywords
This publication has 18 references indexed in Scilit:
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- Support vector machines classification with a very large-scale taxonomyACM SIGKDD Explorations Newsletter, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- A coarse-to-fine strategy for multiclass shape detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Shape indexing using approximate nearest-neighbour search in high-dimensional spacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Unsupervised Learning of Models for RecognitionPublished by Springer Nature ,2000
- Recognition of planar object classesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996