PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913923436904448 |
|---|---|
| author | Wang, Kunyu Fu, Xueyang Bao, Yuanfei Ge, Chengjie Cao, Chengzhi Zhai, Wei Zha, Zheng-Jun |
| author_facet | Wang, Kunyu Fu, Xueyang Bao, Yuanfei Ge, Chengjie Cao, Chengzhi Zhai, Wei Zha, Zheng-Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation Wang, Kunyu Fu, Xueyang Bao, Yuanfei Ge, Chengjie Cao, Chengzhi Zhai, Wei Zha, Zheng-Jun Computer Vision and Pattern Recognition 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. |
| title | PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.02453 |