Sciweavers

ECCV
2010
Springer

Semantic Label Sharing for Learning with Many Categories

13 years 8 months ago
Semantic Label Sharing for Learning with Many Categories
In an object recognition scenario with tens of thousands of categories, even a small number of labels per category leads to a very large number of total labels required. We propose a simple method of label sharing between semantically similar categories. We leverage the WordNet hierarchy to define semantic distance between any two categories and use this semantic distance to share labels. Our approach can be used with any classifier. Experimental results on a range of datasets, upto 80 million images and 75,000 categories in size, show that despite the simplicity of the approach, it leads to significant improvements in performance.
Added 13 Jul 2010
Updated 13 Jul 2010
Type Conference
Year 2010
Where ECCV
Comments (0)