Boosting the Performance of Semi-Supervised Learning with Unsupervised Clustering

Understand

Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels.

• In this paper, we show that ignoring the labels altogether for whole epochs intermittently during training can significantly improve performance in the small sample regime.
• More specifically, we propose to train a network on two tasks jointly.
• The primary classification task is exposed to both the unlabeled and the scarcely annotated data, whereas the secondary task seeks to cluster the data without any labels.