一次蒸馏，终身适应：探索数据集蒸馏用于持续测试时适应
Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation
AI总结：
提出DO-ALL框架，通过数据集蒸馏生成紧凑的合成锚点，在持续测试时适应中提供稳定参考，无需保留原始源数据，提升长期鲁棒性。
摘要：
持续测试时适应（CTTA）旨在通过在线适应无标签数据，在目标域不断变化的情况下保持模型性能。然而，实际部署中由于隐私或许可限制，通常无法保留源数据集，而纯无源CTTA方法在长期分布偏移下容易变得不稳定，遭受累积的自训练错误和灾难性遗忘。我们提出DO-ALL（一次蒸馏，终身适应），一个即插即用的框架，通过数据集蒸馏（DD）以紧凑且保护隐私的形式重新利用源信息。在部署前，DO-ALL执行DD生成一小组合成蒸馏锚点，总结源分布。在适应过程中，每个目标样本与其语义最匹配的锚点对齐，该锚点通过源重放、表示对齐和流形平滑正则化为各种CTTA提供稳定参考。DO-ALL可以无缝集成到现有CTTA算法中，在CIFAR100-C、ImageNet-C和CCC基准测试中持续提升长期鲁棒性。这展示了利用DD在不保留原始源数据的情况下实现稳定连续适应的潜力。代码可在该https URL获取。
英文摘要：
Continual Test-Time Adaptation (CTTA) aims to maintain model performance under evolving target domains by adapting online without labeled data. However, practical deployments often cannot retain the source dataset due to privacy or licensing constraints, and purely source-free CTTA methods tend to become unstable under long-term distribution shift, suffering from compounding self-training errors and catastrophic forgetting. We introduce DO-ALL (Distill Once, Adapt Life-Long), a plug-and-play framework that revisits source information in a compact and privacy-conscious form via Dataset Distillation (DD). Before deployment, DO-ALL performs DD to produce a small set of synthetic distilled anchors that summarize the source distribution. During adaptation, each target sample is matched with its most semantically aligned anchor, which provides a stable reference for various CTTA via source replay, representation alignment, and manifold-smoothing regularization. DO-ALL can be seamlessly integrated into existing CTTA algorithms, consistently improving long-term robustness across CIFAR100-C, ImageNet-C, and the CCC benchmark. This demonstrates the potential of leveraging DD to enable stable and continuous adaptation without retaining raw source data. The code is available at https://github.com/blue-531/DOALL.
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。
