Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffusion-based TTA methods improve robustness for classification to corruptions but rely on gradient guidance, limiting exploration and generalization across distortion types. We propose SteeringTTA, an inference-only framework that adapts Feynman-Kac steering to guide diffusion-based input adaptation for classification with rewards driven by pseudo-label. SteeringTTA maintains multiple particle trajectories, steered by a combination of cumulative top-K probabilities and an entropy schedule, to balance exploration and confidence. On ImageNet-C, SteeringTTA consistently outperforms the baseline without any model updates or source data.

翻译：测试时自适应旨在利用未标注的测试数据更新模型或输入，以纠正深度模型在分布偏移下的性能退化。仅基于输入的扩散式TTA方法提升了分类任务对图像损坏的鲁棒性，但其依赖于梯度引导，限制了在不同失真类型间的探索与泛化能力。我们提出了SteeringTTA，一个仅需推理的框架，该框架将Feynman-Kac引导机制适配于基于扩散的输入自适应过程，通过伪标签驱动的奖励来引导分类。SteeringTTA维护多个粒子轨迹，这些轨迹由累积的Top-K概率与一个熵调度策略共同引导，以平衡探索与置信度。在ImageNet-C数据集上，SteeringTTA在无需任何模型更新或源数据的情况下，始终优于基线方法。