无遗忘学习：无缓冲的持续学习分类
No Forgetting Learning: Buffer-free Continual Learning Classification
AI总结：
本文提出无遗忘学习（NFL），一种无缓冲的持续学习框架，通过分解网络结构并采用逐步冻结协议，实现任务增量学习。NFL+进一步引入欠定自动编码器，提升模型性能并保持内存效率。
摘要：
大多数持续学习（CL）方法通过存储示例在重放缓冲区中保持早期任务性能，引入了与任务数量成比例的内存开销，这在受监管领域引发了隐私问题。我们提出无遗忘学习（NFL），一种无缓冲的类和任务增量学习框架，该框架利用过参数化网络的内在冗余性。NFL将网络分解为共享主干和任务特定的头部，然后应用逐步冻结协议：新能力首先被隔离，共享表示在知识蒸馏下适应，所有组件通过双软目标锚定共同优化。NFL+在此流程中引入欠定自编码器，保留来自先前任务的信息特征并纠正类别不平衡引起的预测偏差。NFL+LoRA进一步将该框架扩展到预训练视觉变换器，通过将更新限制在低秩子空间中，使用Fisher加权正则化，保持恒定的主干内存成本，无论任务数量如何。在CIFAR-100、Tiny-ImageNet和ImageNet-1000上，最多50个增量任务中，NFL+优于所有无缓冲基线，并在仅使用其模型大小的2.53%时匹配基于内存的方法。我们还提出了一种可塑性-稳定性评分，以更平衡地评估贸易-offs。
英文摘要：
Most Continual Learning (CL) methods maintain performance on earlier tasks by storing exemplars in a replay buffer, introducing memory overhead that scales with the number of tasks and raising privacy concerns in regulated domains. We propose No Forgetting Learning (NFL), a buffer-free framework for class- and task-incremental learning that instead exploits the inherent redundancy of overparameterized networks. 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. NFL+ augments this pipeline with an under-complete auto-encoder that preserves informative features from previous tasks and corrects the prediction bias caused by class imbalance. NFL+LoRA further extends the framework to pre-trained Vision Transformers by confining updates to a low-rank subspace with Fisher-weighted regularization, maintaining constant backbone memory cost regardless of the number of tasks. On CIFAR-100, Tiny-ImageNet, and ImageNet-1000 across up to 50 incremental tasks, NFL+ outperforms all buffer-free baselines and matches memory-based methods while requiring only 2.53\% of their model size. We also propose a Plasticity--Stability score for more balanced trade-off evaluation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
