Self-Similarity Prior Distillation for Unsupervised Remote Physiological Measurement
- 30 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10290-10305
Abstract
Remote photoplethysmography (rPPG) is a non-invasive technique that aims to capture subtle variations in facial pixels caused by changes in blood volume resulting from cardiac activities. Most existing unsupervised methods for rPPG tasks focus on the contrastive learning between samples while neglecting the inherent self-similarity prior in physiological signals. In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic temporal self-similarity of cardiac activities. Specifically, we first introduce a physical-prior embedded augmentation technique to mitigate the effect of various types of noise. Then, we tailor a self-similarity-aware network to disentangle more reliable self-similar physiological features. Finally, we develop a hierarchical self-distillation paradigm for self-similarity-aware learning and rPPG signal decoupling. Comprehensive experiments demonstrate that the unsupervised SSPD framework achieves comparable or even superior performance compared to the state-of-the-art supervised methods. Meanwhile, SSPD has the lowest inference time and computation cost among end-to-end models.Keywords
All Related Versions
This publication has 50 references indexed in Scilit:
- TransPPG: two-stream transformer for remote heart rate estimateCCF Transactions on Pervasive Computing and Interaction, 2024
- Contrast-Phys: Unsupervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast2022
- Masked Siamese Networks for Label-Efficient Learning2022
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Unsupervised skin tissue segmentation for remote photoplethysmographyPattern Recognition Letters, 2019
- DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks2018
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Remote heart rate measurement using low-cost RGB face video: a technical literature reviewFrontiers of Computer Science, 2017
- Deep Residual Learning for Image Recognition2016
- One millisecond face alignment with an ensemble of regression trees2014