CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation
TL;DR
Conformal Prediction Active TTA is proposed, which first brings principled, conformal uncertainty with coverage-aware online calibration into ATTA, and consistently outperforms the state-of-the-art ATTA methods by around 5% in accuracy.
Abstract
Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertainty measures and suffer from low data selection efficiency, wasting human annotation budget. We propose Conformal Prediction Active TTA (CPATTA), which first brings principled, conformal uncertainty with coverage-aware online calibration into ATTA. CPATTA employs smoothed conformal scores with a top-$K$ certainty measure, an online weight-update algorithm driven by pseudo coverage, a domain-shift detector that adapts human supervision, and a staged update scheme that balances human-labeled and model-labeled data. Extensive experiments demonstrate that CPATTA consistently outperforms the state-of-the-art ATTA methods by around 5% in accuracy.
