PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Semantic Label Sharing for Learning with Many Categories
Robert Fergus, Hector Bernal, Yair Weiss and Antonio Torralba
Proc. of the IEEE European Conference on Computer Vision 2010.


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, up to 80 million images and 75,000 categories in size, show that despite the simplicity of the approach, it leads to significant improvements in performance.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
ID Code:7147
Deposited By:Talya Meltzer
Deposited On:06 March 2011