提出均匀采样刷新机制，有效减少增量学习中的遗忘问题。
Uniform Herding: Exemplar Replay with Representation Refresh
- 用固定候选池动态刷新各类别代表性样本，适应特征变化。
- 在CIFAR-100上实现44.00%准确率与17.22%遗忘率，优于iCaRL。
- 适合需要长期保持旧类性能的持续学习场景。
随着特征表示的变化，重放需保留早期类别信息，但只能使用有限的活跃样本集。本文提出Uniform Herding方法，将当前活跃样本集按类分配，并利用固定大小的候选池在当前表示下刷新所选样本。在十任务增量学习的CIFAR-100上，采用ResNet-18主干网络、主动集预算M=2,000、检索预算b=64，三组随机种子实验表明，Uniform Herding最终平均准确率达44.00±0.51%，遗忘率为17.22±0.43%，优于iCaRL的42.33±1.20%和24.87±1.11%。在该协议下，替换NME或herding会降低准确率，移除知识蒸馏则增加遗忘。改变检索预算影响较小，而主动集预算变化影响更显著。结果仅限于本协议设置。
原文摘要 · Abstract (English)
As the feature representation changes, replay must preserve the earlier classes. However, only a bounded active exemplar set can be replayed. We propose Uniform Herding, which allocates the current active set across observed classes and uses a bounded candidate pool to refresh their chosen exemplars in the current representation. On CIFAR-100 with ten class-incremental tasks, a ResNet-18 backbone, active budget $M=2{,}000$, retrieval budget $b=64$, and three seeds, Uniform Herding obtains $44.00\pm0.51\%$ final average accuracy and $17.22\pm0.43\%$ forgetting, compared with $42.33\pm1.20\%$ and $24.87\pm1.11\%$ for iCaRL. Within the Uniform Herding protocol, final accuracy decreased when NME or herding was replaced with the tested alternatives, while forgetting increased when distillation was removed. Changing the retrieval budget has a smaller effect across the tested range than changing the active budget. The comparison with iCaRL is end-to-end. It does not isolate the effect of refresh from the other protocol differences. These results are limited to the tested protocol.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。