Self-Training using Selection Network for Semi-supervised Learning

Jisoo Jeong, Seungeui Lee, Nojun Kwak

Abstract

Semi-supervised learning (SSL) is a study that efficiently exploits a large amount of unlabeled data to improve performance in conditions of limited labeled data. Most of the conventional SSL methods assume that the classes of unlabeled data are included in the set of classes of labeled data. In addition, these methods do not sort out useless unlabeled samples and use all the unlabeled data for learning, which is not suitable for realistic situations. In this paper, we propose an SSL method called selective self-training (SST), which selectively decides whether to include each unlabeled sample in the training process. It is designed to be applied to a more real situation where classes of unlabeled data are different from the ones of the labeled data. For the conventional SSL problems which deal with data where both the labeled and unlabeled samples share the same class categories, the proposed method not only performs comparable to other conventional SSL algorithms but also can be combined with other SSL algorithms. While the conventional methods cannot be applied to the new SSL problems, our method does not show any performance degradation even if the classes of unlabeled data are different from those of the labeled data.

Download


Paper Citation


in Harvard Style

Jeong J., Lee S. and Kwak N. (2020). Self-Training using Selection Network for Semi-supervised Learning.In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 23-32. DOI: 10.5220/0008940900230032


in Bibtex Style

@conference{icpram20,
author={Jisoo Jeong and Seungeui Lee and Nojun Kwak},
title={Self-Training using Selection Network for Semi-supervised Learning},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={23-32},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008940900230032},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Self-Training using Selection Network for Semi-supervised Learning
SN - 978-989-758-397-1
AU - Jeong J.
AU - Lee S.
AU - Kwak N.
PY - 2020
SP - 23
EP - 32
DO - 10.5220/0008940900230032