CPATTA: Conformal Supervision Allocation For Active Test-Time Adaptation
Quick summary
arXiv:2509.25692v2 Announce Type: replace-cross 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 driv
Key takeaways
- arXiv:2509.25692v2 Announce Type: replace-cross 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 driv
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments