MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement

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 not an 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 contactless 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 proposed 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 have also demonstrated our proposed method significantly helps reduce the bias in skin type.

References in corpus (8)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Prototypical Networks for Few-shot Learning
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
• Generalized Inner Loop Meta-Learning
• MetaPix: Few-Shot Video Retargeting
• Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars

Cited by in corpus (2)

• MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
• Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets