Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner

TL;DR

This paper introduces Meta-rPPG, a transductive meta-learning approach for remote heart rate estimation that adapts quickly to distributional changes during deployment, achieving state-of-the-art results.

Contribution

The paper proposes a novel transductive meta-learner that enables rapid adaptation to distribution shifts in remote heart rate estimation using rPPG signals.

Findings

Achieves state-of-the-art performance on MAHNOB-HCI dataset.

Effectively adapts to distributional changes during deployment.

Improves robustness of remote heart rate estimation.

Abstract

Remote heart rate estimation is the measurement of heart rate without any physical contact with the subject and is accomplished using remote photoplethysmography (rPPG) in this work. rPPG signals are usually collected using a video camera with a limitation of being sensitive to multiple contributing factors, e.g. variation in skin tone, lighting condition and facial structure. End-to-end supervised learning approach performs well when training data is abundant, covering a distribution that doesn't deviate too much from the distribution of testing data or during deployment. To cope with the unforeseeable distributional changes during deployment, we propose a transductive meta-learner that takes unlabeled samples during testing (deployment) for a self-supervised weight adjustment (also known as transductive inference), providing fast adaptation to the distributional changes. Using this approach, we achieve state-of-the-art performance on MAHNOB-HCI and UBFC-rPPG.