SOURCE-LINKED INTELLIGENCE

Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no access to source data is especially prone to drift or collapse. We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams. SEGA uses a small number of structured erasures to probe how predictive entropy changes as information is removed, and uses the resulting per-sample sensitivity trajectories to coordinate recovery and sample selection rather

Read original source ↗ Open in workspace

recordType

paper

region

Global