arXiv 2502.029982025-02-05cs.LG

用于持续测试时自适应的共形不确定性指示器

Conformal Uncertainty Indicator for Continual Test-Time Adaptation

New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所新模式识别实验室）；China Nuclear Power Engineering Co., LTD（中国核电工程有限公司）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of Computer Science & Engineering, LinYi University（临沂大学计算机科学与工程学院）；School of Electric & Information Engineering, Suzhou University of Science and Technology（苏州科技大学电子与信息工程学院）

Fan Lyu, Hanyu Zhao, Ziqi Shi, Ye Liu, Fuyuan Hu, Zhang Zhang, Liang Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出共形不确定性指示器CUI，通过动态补偿共形预测的覆盖率并筛选可靠伪标签，解决CTTA中错误伪标签累积问题，提升持续测试时自适应性能。

摘要：

持续测试时自适应（CTTA）旨在测试过程中使模型适应顺序变化的领域，依赖伪标签进行自我适应。然而，错误的伪标签会不断累积，导致性能下降。为解决这一问题，我们提出了一种用于CTTA的共形不确定性指示器（CUI），利用共形预测（CP）生成以指定覆盖概率包含真实标签的预测集。由于领域偏移可能使覆盖率低于预期，从而使CP不可靠，我们通过同时度量领域差异和数据差异来动态补偿覆盖率。随后，来自CP的可靠伪标签被有选择地用于增强自适应。实验证实，CUI能有效估计不确定性，并在多种现有CTTA方法上提升自适应性能。

英文摘要：

Continual Test-Time Adaptation (CTTA) aims to adapt models to sequentially changing domains during testing, relying on pseudo-labels for self-adaptation. However, incorrect pseudo-labels can accumulate, leading to performance degradation. To address this, we propose a Conformal Uncertainty Indicator (CUI) for CTTA, leveraging Conformal Prediction (CP) to generate prediction sets that include the true label with a specified coverage probability. Since domain shifts can lower the coverage than expected, making CP unreliable, we dynamically compensate for the coverage by measuring both domain and data differences. Reliable pseudo-labels from CP are then selectively utilized to enhance adaptation. Experiments confirm that CUI effectively estimates uncertainty and improves adaptation performance across various existing CTTA methods.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。