arXiv：cs.AI· Muhammad Huzaifa, Lea Sch\"onherr, Thorsten Eisenhofer·· 4 小时前AI 评分33
WISE-ATTA：预算受限的主动测试时适应中何时请求标签
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
AI 导读
针对现有主动测试时适应（ATTA）方法默认每个测试批次都可请求监督、导致长测试流标注成本过高的问题，研究者提出预算受限 ATTA 设定，即仅少部分测试批次可用标签，并提出 WISE-ATTA 方法，基于在线计算的轻量信号在测试流上分配监督时机。该方法在 ImageNet-C 与 ImageNet-R/K/A 上取得与近期 ATTA 方法相当或更优的性能，同时所需标签大幅减少。
正文
Abstract:Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying supervision. However, most existing ATTA methods implicitly assume that supervision can be requested for every incoming test batch, which can incur substantial annotation cost over long test streams. In this work, we introduce budgeted ATTA in which labels are available for only a fraction of test batches. This formulation shifts the central challenge from deciding what to label within a batch to deciding when supervision should be applied over time. To address this challenge, we propose a budget-aware approach WISE-ATTA that allocates supervision over the test stream based on lightweight signals computed online, prioritizing periods where supervision is likely to be most useful. When a batch is selected for supervision, we further employ a drift-based sample selection criterion that targets samples exhibiting ongoing, unconverged adaptation dynamics, enabling effective updates from a single labeled example. We evaluate this approach on synthetic corruptions (ImageNet-C) and natural distribution shifts (ImageNet-R/K/A). Across settings, WISE-ATTA achieves competitive or improved performance compared to recent ATTA methods while requiring substantially fewer labels. Overall, we find that the timing of supervision is a key, yet underexplored, aspect of active test-time adaptation. Code: this https URL
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.37687 [cs.AI] |
| (or arXiv:2609.37687v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37687 arXiv-issued DOI via DataCite |
Submission history
From: Muhammad Huzaifa [view email]
[v1]
Tue, 29 Sep 2026 14:32:36 UTC (272 KB)
[v2]
Fri, 2 Oct 2026 14:01:43 UTC (272 KB)
来源：arXiv：cs.AI · arxiv.org