Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference

TL;DR

This paper introduces ADDP, a novel continual learning method for remote physiological measurement via rPPG, addressing catastrophic forgetting and simplifying inference, with a new protocol and promising experimental results.

Contribution

We propose ADDP, a continual learning approach with domain prototypes and feature augmentation tailored for rPPG measurement, and establish the first continual learning protocol for this task.

Findings

ADDP effectively reduces forgetting in rPPG continual learning.

The method outperforms existing approaches in experiments.

The new protocol enables fair evaluation of continual learning methods for rPPG.

Abstract

Remote photoplethysmography (rPPG) has gained significant attention in recent years for its ability to extract physiological signals from facial videos. While existing rPPG measurement methods have shown satisfactory performance in intra-dataset and cross-dataset scenarios, they often overlook the incremental learning scenario, where training data is presented sequentially, resulting in the issue of catastrophic forgetting. Meanwhile, most existing class incremental learning approaches are unsuitable for rPPG measurement. In this paper, we present a novel method named ADDP to tackle continual learning for rPPG measurement. We first employ adapter to efficiently finetune the model on new tasks. Then we design domain prototypes that are more applicable to rPPG signal regression than commonly used class prototypes. Based on these prototypes, we propose a feature augmentation strategy to consolidate the past knowledge and an inference simplification strategy to convert potentially forgotten tasks into familiar ones for the model. To evaluate ADDP and enable fair comparisons, we create the first continual learning protocol for rPPG measurement. Comprehensive experiments demonstrate the effectiveness of our method for rPPG continual learning. Source code is available at \url{https://github.com/MayYoY/rPPGDIL}