Semantic label sharing for learning with many categories
Author(s)
Fergus, Rob; Bernal, Hector; Weiss, Yair; Torralba, Antonio
DownloadTorralba_Semantic label.pdf (2.319Mb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
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.
Date issued
2010-09Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Proceedings of the 11th European conference on Computer vision: Part I, ECCV'10
Publisher
Association for Computing Machinery
Citation
Fergus, Rob et al. “Semantic Label Sharing for Learning with Many Categories.” in Proceedings of the 11th European Conference on Computer Vision: Part I. Heraklion, Crete, Sept. 5-11, Greece: Springer-Verlag, 2010. 762-775. (Lecture Notes in Computer Science, Vol. 6311)
Version: Author's final manuscript
ISBN
978-3-642-15548-2
3-642-15548-0