Contrastive Learning for Online Semi-Supervised General Continual Learning

07/12/2022

∙

by   Nicolas Michel, et al.

∙

0

∙

share

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where every data added to memory is labeled using an oracle. Our approach outperforms existing semi-supervised methods when few labels are available, and obtain similar results to state-of-the-art supervised methods while using only 2.6 Split-CIFAR100.