StableSleep: Source-Free Test-Time Adaptation for Sleep Staging with Lightweight Safety Rails
By: Hritik Arasu, Faisal R Jahangiri
Potential Business Impact:
Helps sleep trackers work better on new people.
Sleep staging models often degrade when deployed on patients with unseen physiology or recording conditions. We propose a streaming, source-free test-time adaptation (TTA) recipe that combines entropy minimization (Tent) with Batch-Norm statistic refresh and two safety rails: an entropy gate to pause adaptation on uncertain windows and an EMA-based reset to reel back drift. On Sleep-EDF Expanded, using single-lead EEG (Fpz-Cz, 100 Hz, 30s epochs; R&K to AASM mapping), we show consistent gains over a frozen baseline at seconds-level latency and minimal memory, reporting per-stage metrics and Cohen's k. The method is model-agnostic, requires no source data or patient calibration, and is practical for on-device or bedside use.
Similar Papers
Calibration-Free EEG-based Driver Drowsiness Detection with Online Test-Time Adaptation
Machine Learning (CS)
Detects sleepy drivers without needing to test them first.
Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
Machine Learning (CS)
Makes AI smarter even with messy, changing data.
Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates
Quantitative Methods
Improves medical scans for better diagnoses.