Refining Remote Photoplethysmography Architectures using CKA and Empirical Methods

TL;DR

This paper uses CKA to analyze and refine remote photoplethysmography architectures, identifying optimal depths and reducing redundancies for improved efficiency and performance.

Contribution

It introduces the use of Centered Kernel Alignment (CKA) as a diagnostic tool to refine rPPG model architectures by analyzing layer representations.

Findings

Shallower models learn different representations than deeper ones.

Redundant layers are added beyond a certain depth without significant benefits.

CKA-based diagnostics improve model architecture refinement.

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.