一个池子不够：多簇内存用于实用测试时适应
One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptation
AI总结：
本文提出多簇内存（MCM）以解决实用测试时适应中单池存储的不足，通过多簇组织提升适应稳定性，实验证明在多个数据集上均取得显著提升。
摘要：
测试时适应（TTA）利用未标记的测试数据将预训练模型适应到分布偏移。在实用TTA（PTTA）设置中，测试流具有时间相关性和非独立同分布特性，内存成为稳定适应的关键组件，但现有方法普遍将样本存储在单一无结构池中。本文表明，这种单簇设计与PTTA本质上不匹配：流聚类分析揭示测试流本质上多模态，最优混合成分数量始终远超一个。为弥合这一结构差距，本文提出多簇内存（MCM），一个即插即用框架，利用轻量级像素级统计描述符将存储样本组织成多个簇。MCM引入三种互补机制：基于描述符的簇分配以捕捉不同的分布模式，相邻簇合并（ACC）以通过合并最相似的时间相邻簇限制内存使用，以及均匀簇检索（UCR）以在适应过程中确保所有模式的平衡监督。与三个当前TTA方法结合在CIFAR-10-C、CIFAR-100-C、ImageNet-C和DomainNet上，MCM在所有12种配置中均取得一致改进，最大在ImageNet-C上提升5.00%，在DomainNet上提升12.13%。值得注意的是，这些收益随着分布复杂性增加而增加：更大的标签空间和更大的多模态性从多簇组织中受益最大。基于GMM的内存诊断进一步证实，MCM保持了接近最优的分布平衡、熵和模式覆盖率，而单簇内存表现出持续不平衡和逐步模式损失。这些结果确立了内存组织作为实用测试时适应的关键设计轴。
英文摘要：
Test-time adaptation (TTA) adapts pre-trained models to distribution shifts at inference using only unlabeled test data. Under the Practical TTA (PTTA) setting, where test streams are temporally correlated and non-i.i.d., memory has become an indispensable component for stable adaptation, yet existing methods universally store amples in a single unstructured pool. We show that this single-cluster design is fundamentally mismatched to PTTA: a stream clusterability analysis reveals that test streams are inherently multi-modal, with the optimal number of mixture components consistently far exceeding one. To close this structural gap, we propose Multi-Cluster Memory (MCM), a plug-and-play framework that organizes stored samples into multiple clusters using lightweight pixel-level statistical descriptors. MCM introduces three complementary mechanisms: descriptor-based cluster assignment to capture distinct distributional modes, Adjacent Cluster Consolidation (ACC) to bound memory usage by merging the most similar temporally adjacent clusters, and Uniform Cluster Retrieval (UCR) to ensure balanced supervision across all modes during adaptation. Integrated with three contemporary TTA methods on CIFAR-10-C, CIFAR-100-C, ImageNet-C, and DomainNet, MCM achieves consistent improvements across all 12 configurations, with gains up to 5.00% on ImageNet-C and 12.13% on DomainNet. Notably, these gains scale with distributional complexity: larger label spaces with greater multi-modality benefit most from multi-cluster organization. GMM-based memory diagnostics further confirm that MCM maintains near-optimal distributional balance, entropy, and mode coverage, whereas single-cluster memory exhibits persistent imbalance and progressive mode loss. These results establish memory organization as a key design axis for practical test-time adaptation.
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。
