AI RESEARCH

No Forgetting Learning: Buffer-free Continual Learning Classification

arXiv CS.LG

ArXi:2503.04638v3 Announce Type: replace Most Continual Learning (CL) methods maintain performance on earlier tasks by storing exemplars in a replay buffer, NFL decomposes the network into a shared backbone and task-specific heads, then applies a stepwise freezing protocol: new capabilities are first isolated, shared representations are adapted under knowledge distillation, and all components are jointly refined with dual soft-target anchoring.