Learning by Transferring from Unsupervised Universal Sources - Robotics Institute Carnegie Mellon University

Learning by Transferring from Unsupervised Universal Sources

Conference Paper, Proceedings of 30th AAAI Conference on Artificial Intelligence (AAAI '16), pp. 2187 - 2193, February, 2016

Abstract

Category classifiers trained from a large corpus of annotated data are widely accepted as the sources for (hypothesis) transfer learning. Sources generated in this way are tied to a particular set of categories, limiting their transferability across a wide spectrum of target categories. In this paper, we address this largely-overlooked yet fundamental source problem by both introducing a systematic scheme for generating universal source hypotheses and proposing a principled, scalable approach to automatically tuning the transfer process. Our approach is based on the insights that expressive source hypotheses could be generated without any supervision and that a sparse combination of such hypotheses facilitates recognition of novel categories from few samples. We demonstrate improvements over the state-of-the-art on object and scene classification in the small sample size regime.

BibTeX

@conference{Wang-2016-5485,
author = {Yuxiong Wang and Martial Hebert},
title = {Learning by Transferring from Unsupervised Universal Sources},
booktitle = {Proceedings of 30th AAAI Conference on Artificial Intelligence (AAAI '16)},
year = {2016},
month = {February},
pages = {2187 - 2193},
}