BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
BayaHAR is presented, a gradient-free framework that repurposes pretrained HAR classifiers as Prototypical Networks using prior prototypes that preserve zero-shot performance while regularizing adaptation, and enables efficient and robust on-device personalization of preexisting HAR classifiers.
Maximilian Burzer, T. Riedel, Michael Beigl et al.
· Proceedings of the 2026 ACM... · 1 citation