Abstract
There are large individual differences in physiological processes, making designing personalized health sensing algorithms challenging. Existing machine learning systems struggle to generalize well to unseen subjects or contexts and can often contain problematic biases. Video-based physiological measurement is no exception. Therefore, learning personalized or customized models from a small number of unlabeled samples is very attractive as it would allow fast calibrations to improve generalization and help correct biases. In this paper, we present a novel meta-learning approach called MetaPhys for personalized video-based cardiac measurement for non-contact pulse and heart rate monitoring. Our method uses only 18-seconds of video for customization and works effectively in both supervised and unsupervised manners. We evaluate our approach on two benchmark datasets and demonstrate superior performance in cross-dataset evaluation with substantial reductions (42% to 44%) in errors compared with state-of-the-art approaches. We also find that our method leads to large reductions in bias due to skin type.
