Transfer learning

Transfer learning improves frailty classification performance in silico.

“selectively freezing low-level gait representations while allowing higher-level features to adapt yields more stable and generalizable performance than either full fine-tuning or rigid freezing”

In silico

The Gait Signature of Frailty: Transfer Learning based Deep Gait Models for Scalable Frailty Assessment

arXiv (Cornell University)·25 Mar 2026Preprint