均匀聚集：带表示刷新的样本回放

中文摘要 AI 辅助

随着特征表示发生变化，回放必须保留先前的类别，但仅能回放有界的活跃样本集。我们提出均匀聚集（Uniform Herding）方法，该方法将当前活跃集分配到已观测类别中，并利用有界候选池在当前表示中刷新所选样本。在包含10个类增量任务的CIFAR-100数据集上，使用ResNet-18作为骨干网络，活跃预算M=2000，检索预算b=64，且采用3个随机种子的设置下，Uniform Herding获得的最终平均准确率为44.00±0.51%，遗忘率为17.22±0.43%；相比之下，iCaRL的对应指标为42.33±1.20%和24.87±1.11%。在Uniform Herding协议内，当用测试的替代方法替换NME或聚集（herding）时，最终准确率会下降；当移除蒸馏（distillation）时，遗忘率会上升。在测试范围内，改变检索预算的影响小于改变活跃预算的影响。与iCaRL的比较是端到端的，未将刷新的效果与协议的其他差异隔离开，这些结果仅适用于所测试的协议。

英文摘要

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.

发表机构

• Neryva（内里瓦）

机构由 AI 辅助整理，请以论文原文为准。