WISE-ATTA：在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
- CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对预算受限的主动测试时适应，提出WISE-ATTA方法，通过在线信号分配监督时机并利用漂移选择样本，在减少标签需求的同时保持或提升性能。
AI中文摘要：
主动测试时适应（ATTA）通过在推理过程中更新部署模型并选择性查询监督来提高在分布偏移下的鲁棒性。然而，大多数现有的ATTA方法隐含地假设可以对每个到来的测试批次请求监督，这在长测试流上会带来大量的标注成本。在这项工作中，我们引入了预算受限的ATTA，其中标签仅对一部分测试批次可用。这种设定将核心挑战从决定在批次内标注什么转变为决定在时间上何时应用监督。为了解决这一挑战，我们提出了一种预算感知方法WISE-ATTA，它基于在线计算的轻量级信号在测试流上分配监督，优先考虑监督可能最有用的时期。当选择批次进行监督时，我们进一步采用基于漂移的样本选择标准，针对表现出持续、未收敛的适应动态的样本，从而能够从单个标记示例中进行有效更新。我们在合成损坏（ImageNet-C）和自然分布偏移（ImageNet-R/K/A）上评估了该方法。在各种设置中，WISE-ATTA相比最近的ATTA方法实现了具有竞争力或更好的性能，同时所需的标签明显更少。总体而言，我们发现监督的时机是主动测试时适应中一个关键但尚未充分探索的方面。代码：此https URL。
英文摘要：
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: https://github.com/Muhammad-Huzaifaa/WISE-ATTA
