可靠性门控的源锚定用于持续测试时间适应
Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
AI总结：
该研究提出了一种可靠性门控的源锚定方法（RMemSafe），用于持续测试时间适应（CTTA），通过利用冻结源的归一化预测熵来抑制所有显式源耦合使用，从而在源可靠性下降时自动关闭源锚定和一致性过滤器，提升模型在持续腐蚀任务中的性能。
摘要：
持续测试时间适应（CTTA）在在线更新预训练模型时，将模型锚定到一个冻结的源检查点上。然而，当源可靠性下降时，这种锚定方式会失效。在CCCHard数据集上，ResNet-50源的top-1准确率下降至约1.3%，而现有源锚定CTTA方法仍然使用相同的锚定强度。本文提出RMemSafe，一种基于ROID的可靠性门控扩展方法，利用冻结源的归一化预测熵来衰减目标函数中的所有显式源耦合使用。当源后验接近均匀分布时，门控关闭：源锚定和一致性过滤器消失，目标函数减少为源无关的回退，包含ROID的基本损失加上边际校准。结合ASR，RMemSafe在8个匹配分割的持续腐蚀单元中实现了最低的错误率，并在所有9个单元中是最佳的重置方法，比ROID+ASR在ResNet-50上提升1.05个百分点，在ViT-B/16上提升0.48个百分点。受控的源退化扫描显示，其危害斜率比ROID+ASR浅1.13倍，与渐进衰减预测一致。熵门控检测到高熵源崩溃，而非自信错误的低熵源；该范围被明确评估和讨论。
英文摘要：
Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source checkpoint. This anchor is useful only when the source remains reliable. On CCC-Hard, however, a ResNet-50 source falls to approximately $1.3\%$ top-$1$ accuracy, while existing source-anchored CTTA methods continue applying the same anchor strength. We call this failure mode blind anchoring and propose RMemSafe, a reliability-gated extension of ROID that uses the frozen source's normalized predictive entropy to attenuate all explicit source-coupled uses in the objective. When the source posterior approaches uniformity, the gate closes: the source anchor and agreement filter vanish, and the objective reduces to a source-agnostic fallback comprising ROID's base losses plus marginal calibration. Combined with ASR, RMemSafe achieves the lowest error on $8$ of $9$ matched-split continual-corruption cells and is the best reset-based method on all $9$, improving ROID+ASR by $1.05$~pp on ResNet-50 and $0.48$~pp on ViT-B/16. A controlled source-degradation sweep shows a $1.13{\times}$ shallower harm slope than ROID+ASR, consistent with the graceful-decay prediction. The entropy gate detects high-entropy source collapse, not confidently wrong low-entropy sources; this scope is explicitly evaluated and discussed.
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。
