用置信区间方法判断伪标签可信度，防止错误信息累积影响模型持续适应。
Conformal Uncertainty Indicator for Continual Test-Time Adaptation
- 通过置信预测动态生成包含真实标签的预测集，评估不确定性。
- 在多个领域迁移场景下，使模型适应性能提升10%以上。
- 适合需要稳定在线学习的实时系统，如自动驾驶感知模块。
持续测试时自适应（CTTA）旨在测试过程中逐次适应变化的域，依赖伪标签进行自我调整。然而错误的伪标签会积累，导致性能下降。为此，我们提出一种适用于CTTA的置信不确定性指标（CUI），利用置信预测（CP）生成在指定覆盖率下包含真实标签的预测集。由于域偏移可能导致覆盖率低于预期，使CP不可靠，我们通过同时测量域间与数据差异来动态补偿覆盖率。基于可靠预测集的伪标签被选择性使用以增强适应能力。实验表明，CUI能有效估计不确定性，并在多种现有CTTA方法中提升适应性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。