缓解持续测试时适应模型中的偏差
Mitigating the Bias in the Model for Continual Test-Time Adaptation
AI总结：
针对持续测试时适应中模型因链式分布变化而产生的类别预测偏差，本文提出基于可靠样本的类别级 EMA 目标原型聚类与源原型锚定对齐方法，在现有 CTA 方法上显著提升性能且开销很小。
摘要：
持续测试时适应（Continual Test-Time Adaptation，CTA）是一项具有挑战性的任务，旨在使源预训练模型适应不断变化的目标域。在 CTA 设置中，模型不知道目标域何时发生变化，因此在测试期间会面临流式输入分布的剧烈变化。关键挑战在于以在线方式持续调整模型，使其适应不断变化的目标域。我们发现，当模型不断适应目标数据的链式分布时，会表现出高度偏差的预测：它对某些类别的预测频率高于其他类别，从而产生不准确且过度自信的预测。本文缓解这一问题，以提升 CTA 场景下的性能。为缓解偏差问题，我们利用可靠的目标样本构建按类别的指数移动平均目标原型，并用这些原型对目标特征进行按类别聚类。此外，我们通过将目标特征锚定到其对应的源原型，力求使目标分布与源分布对齐。通过大量实验，所提方法在现有 CTA 方法之上应用时取得了显著的性能提升，且没有产生大量的适应时间开销。
英文摘要：
Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, thus facing a drastic change in the distribution of streaming inputs during the test-time. The key challenge is to keep adapting the model to the continually changing target domains in an online manner. We find that a model shows highly biased predictions as it constantly adapts to the chaining distribution of the target data. It predicts certain classes more often than other classes, making inaccurate over-confident predictions. This paper mitigates this issue to improve performance in the CTA scenario. To alleviate the bias issue, we make class-wise exponential moving average target prototypes with reliable target samples and exploit them to cluster the target features class-wisely. Moreover, we aim to align the target distributions to the source distribution by anchoring the target feature to its corresponding source prototype. With extensive experiments, our proposed method achieves noteworthy performance gain when applied on top of existing CTA methods without substantial adaptation time overhead.
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。
