PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
This addresses the challenge of adapting models to changing environments during inference for machine learning applications, representing an incremental advance by leveraging underutilized geometric priors.
The paper tackled the problem of continual test-time adaptation (CTTA) by proposing PAID, a method that preserves pairwise angular structure from pre-trained weights, achieving consistent improvements over state-of-the-art methods on four benchmarks.
Continual Test-Time Adaptation (CTTA) aims to online adapt a pre-trained model to changing environments during inference. Most existing methods focus on exploiting target data, while overlooking another crucial source of information, the pre-trained weights, which encode underutilized domain-invariant priors. This paper takes the geometric attributes of pre-trained weights as a starting point, systematically analyzing three key components: magnitude, absolute angle, and pairwise angular structure. We find that the pairwise angular structure remains stable across diverse corrupted domains and encodes domain-invariant semantic information, suggesting it should be preserved during adaptation. Based on this insight, we propose PAID (Pairwise Angular-Invariant Decomposition), a prior-driven CTTA method that decomposes weight into magnitude and direction, and introduces a learnable orthogonal matrix via Householder reflections to globally rotate direction while preserving the pairwise angular structure. During adaptation, only the magnitudes and the orthogonal matrices are updated. PAID achieves consistent improvements over recent SOTA methods on four widely used CTTA benchmarks, demonstrating that preserving pairwise angular structure offers a simple yet effective principle for CTTA.