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.

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Gregory Griffin, Darya Perona
• Keywords: Computer Vision, CVPR 2008, Greedy Algorithm, Log Ncat Complexity, Specific Classification Algorithm, Sub-linear Classification Costs, Visual Categorization Algorithms