AI RESEARCH
Prototypical Exemplar Condensation for Memory-efficient Online Continual Learning
arXiv CS.AI
•
ArXi:2603.13804v1 Announce Type: cross Rehearsal-based continual learning (CL) mitigates catastrophic forgetting by maintaining a subset of samples from previous tasks for replay. Existing studies primarily focus on optimizing memory storage through coreset selection strategies. While these methods are effective, they typically require storing a substantial number of samples per class (SPC), often exceeding 20, to maintain satisfactory performance.