Empirical Perspectives on One-Shot Semi-supervised Learning
This work addresses the problem of reducing labeling effort for deep learning practitioners, but it is incremental as it builds on existing methods like FixMatch.
The paper investigates one-shot semi-supervised learning, where only one labeled sample per class is used with unlabeled data, to identify factors like uneven class accuracy that hinder high performance on Cifar-10, aiming to improve adoption for new applications.
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.