一次蒸餾，終身適應：探索數據集蒸餾於持續測試時適應

摘要

持續測試時間自適應（CTTA）旨在透過無標籤資料的線上自適應，在不斷變化的目標領域中維持模型性能。然而，實際部署時常因隱私或授權限制而無法保留原始資料集，而純粹無來源的CTTA方法在長期分佈偏移下容易變得不穩定，遭受疊加式自訓練錯誤與災難性遺忘。我們提出DO-ALL（一次性蒸餾，終身自適應），這是一個即插即用的框架，透過資料集蒸餾（DD）以緊湊且注重隱私的形式重新審視來源資訊。在部署前，DO-ALL執行DD以產生一組小型合成蒸餾錨點，總結來源資料分佈。在自適應過程中，每個目標樣本會與其語義最相似的錨點匹配，該錨點透過來源重播、表徵對齊及流形平滑正則化，為各種CTTA提供穩定的參考。DO-ALL可無縫整合至現有CTTA演算法，持續提升CIFAR100-C、ImageNet-C及CCC基準測試中的長期穩健性。這展現了利用DD在無需保留原始來源資料的情況下實現穩定且連續自適應的潛力。程式碼已公開於 https://github.com/blue-531/DOALL。

English

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.