测试时自适应何时可从无标签证据中识别？

中文摘要 AI 辅助

测试时自适应（TTA）提供了多种无需标签即可更新已部署模型的方法，但选择错误的更新方式可能会使原本强大的源模型性能变得更差。因此，近期方法试图从无标签测试数据中预测哪种自适应方式有效。我们提出了一个前置问题：提供给选择器的证据是否包含足够的信息来确定最佳行动？我们证明，即使使用完美的选择器，这也不能得到保证。如果观测通道使两种部署看起来相同而它们的TTA排名不同，则从该通道进行可靠选择是不可能的；更丰富的证据只有在解决相关歧义时才能恢复决策。我们在有限批次高斯TTA模型中精确划定了这一边界，在该模型中，对于小偏移，不采取任何行动优于均值重新居中，而重新居中在超过唯一临界偏移后获胜，且边界随$1/\sqrt n$缩小。在CIFAR-100-C和DomainNet-126上的公开基准研究表明，现代TTA方法存在同样的失败模式：仅改变部署结构就能逆转oracle行动，而全局无序证据保持不变。这一结果提供了一种实用方法，可将通常混合在一起的两种失败模式区分开来：弱选择器与无法支持所需决策的信息通道。

英文摘要

Test-time adaptation (TTA) offers many ways to update a deployed model without labels, but choosing the wrong update can make a strong source model worse. Recent methods therefore try to predict which adaptation will work from unlabeled test data. We ask a prior question: does the evidence given to the selector contain enough information to determine the best action at all? We show that this is not guaranteed, even with a perfect selector. If an observation channel makes two deployments look the same while their TTA rankings differ, reliable selection is impossible from that channel; richer evidence can restore the decision only when it resolves the relevant ambiguity. We make this boundary exact in a finite-batch Gaussian TTA model, where doing nothing beats mean recentering for small shifts, recentering wins beyond a unique critical shift, and the boundary shrinks as $1/\sqrt n$. Public benchmark studies on CIFAR-100-C and DomainNet-126 show the same failure mode with modern TTA methods: changing only deployment structure can reverse the oracle action while global order-blind evidence remains unchanged. The result is a practical way to separate two failure modes that are usually mixed together: a weak selector versus an information channel that cannot support the desired decision in the first place.

发表机构

• Nanyang Technological University（南洋理工大学）
• Institute for Digital Molecular Analytics and Science（数字分子分析与科学研究所）
• School of Electrical and Electronic Engineering（电气与电子工程学院）

机构由 AI 辅助整理，请以论文原文为准。