SOURCE-LINKED INTELLIGENCE

Should This Case Be Adapted? Prediction Fragmentation Controls Test-Time Adaptation

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Episodic test-time adaptation resets a frozen segmenter to source weights $M_0$ on each case and adapts for a fixed step count. A fixed horizon conflates a cohort-level question, how far to adapt, with an irreducibly per-case one, whether this case should be adapted at all. Cohort means hide that decision: on cross-vendor cardiac MRI the mean $Δ$Dice from adaptation is statistically indistinguishable from zero while 58.7% of cases are individually made worse. We quantify this harm as harmful accepted area (HA), the harmful fraction of the edited area a controller deploys. Held-out tuning gives

Read original source ↗ Open in workspace

recordType

paper

region

Global