混合记忆回放：融合真实数据与蒸馏数据用于类增量学习
Hybrid Memory Replay: Blending Real and Distilled Data for Class Incremental Learning
AI总结：
本文提出混合记忆回放方法，通过从历史检查点滑动窗口蒸馏合成数据并优化真实样本选择，融合两类样本优势以缓解类增量学习中的灾难性遗忘，在有限缓冲区下显著优于现有回放基线。
摘要：
增量学习（IL）旨在从当前任务中获取新知识，同时保留从先前任务中学到的知识。基于回放的IL方法将先前任务的一组样本存储在缓冲区中，并在学习新任务时回放这些样本。然而，通常缓冲区大小有限，无法存储足够的真实样本以保留先前任务的知识。相比之下，数据蒸馏（DD）通过将大型真实数据集压缩为规模更小、信息更紧凑的合成样本集，可以减小样本缓冲区的规模。然而，随着合成样本数量的增加，DD在IL上的性能增益会迅速消失。为了克服真实数据缓冲区和合成数据缓冲区的不足，我们转而优化一种包含两类数据的混合记忆。具体而言，我们对DD提出了一种创新性修改，即从历史检查点的滑动窗口（而不是多条训练轨迹上的检查点）中蒸馏合成数据。以合成数据为条件，我们随后优化真实样本的选择，以对DD目标提供互补性改进。优化后的混合记忆结合了合成样本与真实样本的优势，在样本缓冲区大小受限的情况下有效缓解了类增量学习（CIL）中的灾难性遗忘。值得注意的是，我们的方法可以无缝集成到大多数现有的基于回放的CIL模型中。在多个基准上的大量实验表明，我们的方法显著优于现有的基于回放的基线方法。
英文摘要：
Incremental learning (IL) aims to acquire new knowledge from current tasks while retaining knowledge learned from previous tasks. Replay-based IL methods store a set of exemplars from previous tasks in a buffer and replay them when learning new tasks. However, there is usually a size-limited buffer that cannot store adequate real exemplars to retain the knowledge of previous tasks. In contrast, data distillation (DD) can reduce the exemplar buffer's size, by condensing a large real dataset into a much smaller set of more information-compact synthetic exemplars. Nevertheless, DD's performance gain on IL quickly vanishes as the number of synthetic exemplars grows. To overcome the weaknesses of real-data and synthetic-data buffers, we instead optimize a hybrid memory including both types of data. Specifically, we propose an innovative modification to DD that distills synthetic data from a sliding window of checkpoints in history (rather than checkpoints on multiple training trajectories). Conditioned on the synthetic data, we then optimize the selection of real exemplars to provide complementary improvement to the DD objective. The optimized hybrid memory combines the strengths of synthetic and real exemplars, effectively mitigating catastrophic forgetting in Class IL (CIL) when the buffer size for exemplars is limited. Notably, our method can be seamlessly integrated into most existing replay-based CIL models. Extensive experiments across multiple benchmarks demonstrate that our method significantly outperforms existing replay-based baselines.
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。
