Semantic Label Sharing for Learning with Many Categories
Abstract
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.
Cite
Text
Fergus et al. "Semantic Label Sharing for Learning with Many Categories." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15549-9_55Markdown
[Fergus et al. "Semantic Label Sharing for Learning with Many Categories." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/fergus2010eccv-semantic/) doi:10.1007/978-3-642-15549-9_55BibTeX
@inproceedings{fergus2010eccv-semantic,
title = {{Semantic Label Sharing for Learning with Many Categories}},
author = {Fergus, Robert and Bernal, Hector and Weiss, Yair and Torralba, Antonio},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {762-775},
doi = {10.1007/978-3-642-15549-9_55},
url = {https://mlanthology.org/eccv/2010/fergus2010eccv-semantic/}
}