Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity

TL;DR

This paper introduces model similarity metrics to measure domain shifts in remote photoplethysmography, enabling better model selection in real-world scenarios without ground truth, and shows significant performance improvements.

Contribution

It proposes novel model similarity metrics for domain shift detection in rPPG and demonstrates their effectiveness in model selection without requiring ground truth data.

Findings

High correlation between proposed metrics and empirical performance

DS-diff metric works without access to ground truth

13.9% performance improvement in model selection

Abstract

Domain shift differences between training data for deep learning models and the deployment context can result in severe performance issues for models which fail to generalize. We study the domain shift problem under the context of remote photoplethysmography (rPPG), a technique for video-based heart rate inference. We propose metrics based on model similarity which may be used as a measure of domain shift, and we demonstrate high correlation between these metrics and empirical performance. One of the proposed metrics with viable correlations, DS-diff, does not assume access to the ground truth of the target domain, i.e. it may be applied to in-the-wild data. To that end, we investigate a model selection problem in which ground truth results for the evaluation domain is not known, demonstrating a 13.9% performance improvement over the average case baseline.