LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement
Quick Take
The LQ-rPPG framework enhances remote photoplethysmography by using a label-quantization module to reduce noise in training labels, leading to robust rPPG estimation. It achieves an 88% reduction in parameters and a 191% increase in throughput, demonstrating strong performance across multiple datasets.
Key Points
- LQ-rPPG uses a label quantization module to improve training label quality.
- The framework reduces overfitting by refining rPPG signals under hierarchical supervision.
- Achieves 88% reduction in parameters and 191% increase in throughput.
- Demonstrates strong performance in intra- and cross-dataset evaluations.
- Code is available on GitHub for further research and application.
Article Content
From source RSS / original summaryarXiv:2605. 23174v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of physiological signals from facial videos, offering strong potential for remote healthcare and daily health monitoring. Driven by this potential, various deep learning-based rPPG methods have been proposed to improve rPPG estimation. However, previous deep learning-based rPPG methods have paid little attention to the quality of training labels and their impact on model learning.
Contact-based PPG signals used as training labels often contain noise and variability caused by motion artifacts, inconsistent sensor contact, and morphological distortions. Such label inconsistency can lead models to overfit to the label noise and variability and consequently degrade generalization performance. To address this issue, we propose LQ-rPPG, a label-quantized coarse-to-fine learning framework for robust rPPG estimation.
LQ-rPPG consists of a label quantization module and a coarse-to-fine rPPG estimation model. The label quantization module transforms continuous PPG signals into multi-bit quantized pseudo labels with reduced noise and variability. The coarse-to-fine estimation model progressively refines rPPG signals under hierarchical supervision guided by the multi-bit pseudo labels. This design alleviates overfitting to label-specific variations and enables the model to learn structured and consistent representations.
As a result, LQ-rPPG achieves robust and generalizable rPPG estimation even under challenging conditions. Experiments on multiple benchmark datasets demonstrate that LQ-rPPG achieves strong performance in both intra- and cross-dataset evaluations, while reducing parameters and multiply-accumulate operations by 88% and 29%, respectively, and increasing throughput by 191%. The code is available at https://github. com/Anonymous-repo-code/LQ-rPPG.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.