Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
This addresses the challenge of continual learning in real-world applications where labeled data is scarce, offering a more efficient solution.
The paper tackles the problem of continual learning with limited labeled data by proposing a continual semi-supervised learning method that uses contrastive interpolation consistency. It shows that with only 25% supervision, their method outperforms state-of-the-art methods trained under full supervision.
Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this clashes with many real-world applications: gathering labeled data, which is in itself tedious and expensive, becomes infeasible when data flow as a stream. This work explores Continual Semi-Supervised Learning (CSSL): here, only a small fraction of labeled input examples are shown to the learner. We assess how current CL methods (e.g.: EWC, LwF, iCaRL, ER, GDumb, DER) perform in this novel and challenging scenario, where overfitting entangles forgetting. Subsequently, we design a novel CSSL method that exploits metric learning and consistency regularization to leverage unlabeled examples while learning. We show that our proposal exhibits higher resilience to diminishing supervision and, even more surprisingly, relying only on 25% supervision suffices to outperform SOTA methods trained under full supervision.