Empirical Perspectives on One-Shot Semi-supervised Learning
Abstract
One of the greatest obstacles in the adoption of deep neural networks for new applications is that training the network typically requires a large number of manually labeled training samples. We empirically investigate the scenario where one has access to large amounts of unlabeled data but require labeling only a single prototypical sample per class in order to train a deep network (i.e., one-shot semi-supervised learning). Specifically, we investigate the recent results reported in FixMatch for one-shot semi-supervised learning to understand the factors that affect and impede high accuracies and reliability for one-shot semi-supervised learning of Cifar-10. For example, we discover that one barrier to one-shot semi-supervised learning for high-performance image classification is the unevenness of class accuracy during the training. These results point to solutions that might enable more widespread adoption of one-shot semi-supervised training methods for new applications.
Cite
@article{arxiv.2004.04141,
title = {Empirical Perspectives on One-Shot Semi-supervised Learning},
author = {Leslie N. Smith and Adam Conovaloff},
journal= {arXiv preprint arXiv:2004.04141},
year = {2020}
}
Comments
Short paper with interesting results pointing to further investigation