通过保持权重角度结构，实现更稳定的持续测试时自适应。
PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
- 将模型权重分解为大小和方向，用正交矩阵旋转方向
- 在四个基准上优于当前最优方法，提升稳定性和性能
- 适合需要持续适应新环境的部署场景
持续测试时自适应（CTTA）旨在推理过程中在线调整预训练模型以应对变化的环境。现有方法多关注目标数据，忽视了预训练权重中蕴含的未充分利用的域不变先验信息。本文从预训练权重的几何特性出发，系统分析了幅度、绝对角度和成对角度结构三个关键成分。发现成对角度结构在多种损坏域间保持稳定，编码了域不变语义信息，应予以保留。基于此，提出PAID（成对角度不变分解）方法：将权重分解为幅度与方向，通过Householder反射引入可学习正交矩阵，全局旋转方向的同时保持成对角度结构。适配过程中仅更新幅度和正交矩阵。在四个广泛使用的CTTA基准上，PAID持续超越近期SOTA方法，证明保留成对角度结构是CTTA的一种简单而有效原则。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。