Contrastive Learning for Online Semi-Supervised General Continual Learning
This addresses the challenge of efficient learning in continual settings with limited labeled data, which is incremental but offers practical gains.
The paper tackles the problem of online continual learning with missing labels by proposing SemiCon, a contrastive loss for partly labeled data, achieving results similar to state-of-the-art supervised methods using only 2.6% of labels on Split-CIFAR10 and 10% on Split-CIFAR100.
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% of labels on Split-CIFAR10 and 10% of labels on Split-CIFAR100.