Refining Remote Photoplethysmography Architectures using CKA and Empirical Methods
Preprint
Abstract
Model architecture refinement is a challenging task in deep learning research fields such as remote photoplethysmography (rPPG). One architectural consideration, the depth of the model, can have significant consequences on the resulting performance. In rPPG models that are overprovisioned with more layers than necessary, redundancies exist, the removal of which can result in faster training and reduced computational load at inference time. With too few layers the models may exhibit sub-optimal error rates. We apply Centered Kernel Alignment (CKA) to an array of rPPG architectures of differing depths, demonstrating that shallower models do not learn the same representations as deeper models, and that after a certain depth, redundant layers are added without significantly increased functionality. An empirical study confirms how the architectural deficiencies discovered using CKA impact performance, and we show how CKA as a diagnostic can be used to refine rPPG architectures.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Unifying frame rate and temporal dilations for improved remote pulse detectionComputer Vision and Image Understanding, 2021
- Deception Detection and Remote Physiological Monitoring: A Dataset and Baseline Experimental Results2021
- RhythmNet: End-to-End Heart Rate Estimation From Face via Spatial-Temporal RepresentationIEEE Transactions on Image Processing, 2019
- Unsupervised skin tissue segmentation for remote photoplethysmographyPattern Recognition Letters, 2019
- Algorithmic Principles of Remote PPGIEEE Transactions on Biomedical Engineering, 2016
- Robust Pulse Rate From Chrominance-Based rPPGIEEE Transactions on Biomedical Engineering, 2013
- Non-contact, automated cardiac pulse measurements using video imaging and blind source separationOptics Express, 2010
- Remote plethysmographic imaging using ambient lightOptics Express, 2008
- Heart rate measurement based on a time-lapse imageMedical Engineering & Physics, 2006
- Content and cluster analysis: Assessing representational similarity in neural systemsPhilosophical Psychology, 2000