Conformal Uncertainty Indicator for Continual Test-Time Adaptation
This work addresses a specific issue in CTTA for machine learning models adapting to changing domains, but it is incremental as it builds on existing CTTA methods.
The paper tackles the problem of incorrect pseudo-labels causing performance degradation in Continual Test-Time Adaptation (CTTA) by proposing a Conformal Uncertainty Indicator (CUI) that uses Conformal Prediction to generate reliable pseudo-labels, resulting in improved adaptation performance across various CTTA methods.
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.