Adaptive and Balanced Re-initialization for Long-timescale Continual Test-time Domain Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914310466306048 |
|---|---|
| author | Wang, Yanshuo Tong, Jinguang Lan, Jun Wang, Weiqiang Zhu, Huijia Chen, Haoxing Li, Xuesong Hong, Jie |
| author_facet | Wang, Yanshuo Tong, Jinguang Lan, Jun Wang, Weiqiang Zhu, Huijia Chen, Haoxing Li, Xuesong Hong, Jie |
| contents | Continual test-time domain adaptation (CTTA) aims to adjust models so that they can perform well over time across non-stationary environments. While previous methods have made considerable efforts to optimize the adaptation process, a crucial question remains: Can the model adapt to continually changing environments over a long time? In this work, we explore facilitating better CTTA in the long run using a re-initialization (or reset) based method. First, we observe that the long-term performance is associated with the trajectory pattern in label flip. Based on this observed correlation, we propose a simple yet effective policy, Adaptive-and-Balanced Re-initialization (ABR), towards preserving the model's long-term performance. In particular, ABR performs weight re-initialization using adaptive intervals. The adaptive interval is determined based on the change in label flip. The proposed method is validated on extensive CTTA benchmarks, achieving superior performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06328 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive and Balanced Re-initialization for Long-timescale Continual Test-time Domain Adaptation Wang, Yanshuo Tong, Jinguang Lan, Jun Wang, Weiqiang Zhu, Huijia Chen, Haoxing Li, Xuesong Hong, Jie Computer Vision and Pattern Recognition Continual test-time domain adaptation (CTTA) aims to adjust models so that they can perform well over time across non-stationary environments. While previous methods have made considerable efforts to optimize the adaptation process, a crucial question remains: Can the model adapt to continually changing environments over a long time? In this work, we explore facilitating better CTTA in the long run using a re-initialization (or reset) based method. First, we observe that the long-term performance is associated with the trajectory pattern in label flip. Based on this observed correlation, we propose a simple yet effective policy, Adaptive-and-Balanced Re-initialization (ABR), towards preserving the model's long-term performance. In particular, ABR performs weight re-initialization using adaptive intervals. The adaptive interval is determined based on the change in label flip. The proposed method is validated on extensive CTTA benchmarks, achieving superior performance. |
| title | Adaptive and Balanced Re-initialization for Long-timescale Continual Test-time Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.06328 |