SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation

Jihyun Yu, Yoojin Oh, Wonho Bae, Mingyu Kim, Junhyug Noh

Keywords: Test‐time adaptation, Diffusion models, Feynman–Kac steering

TL;DR: SteeringTTA applies SMC‐based Feynman–Kac steering with pseudo‐label rewards to diffusion‐based input restoration for robust, update‐free test-time adaptation.

Abstract: 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.

Submission Number: 45