[Summary] Semi-supervised Learning Made Simple with Self-supervised Clustering
TL;DR In self-supervised learning there are no guarantees that representations will organize the clusters according to their semantic classes. When labels are partially available the authors propose to replace the cluster centroids with class prototypes learned with supervision. In this way, unlabeled samples will be clustered around the class prototypes, guided by the self-supervised clustering-based objective. Method The method trains a model by jointly optimize a supervised loss on labeled data and a self-supervised loss on unlabeled data using the same loss function (cross-entropy)....