FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Xiao, He, Dengbo, Wang, Jiyao, Wu, Kaishun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914145633304576
author Yang, Xiao
He, Dengbo
Wang, Jiyao
Wu, Kaishun
author_facet Yang, Xiao
He, Dengbo
Wang, Jiyao
Wu, Kaishun
contents Remote physiological measurement gained wide attention, while it requires collecting users' privacy-sensitive information, and existing contactless measurements still rely on labeled client data. This presents challenges when we want to further update real-world deployed models with numerous user data lacking labels. To resolve these challenges, we instantiate a new protocol called Federated Unsupervised Domain Generalization (FUDG) in this work. Subsequently, the \textbf{Fed}erated \textbf{H}eterogeneous \textbf{U}nsupervised \textbf{G}eneralization (\textbf{FedHUG}) framework is proposed and consists of: (1) Minimal Bias Aggregation module dynamically adjusts aggregation weights based on prior-driven bias evaluation to cope with heterogeneous non-IID features from multiple domains. (2) The Global Distribution-aware Learning Controller parameterizes the label distribution and dynamically manipulates client-specific training strategies, thereby mitigating the server-client label distribution skew and long-tail issue. The proposal shows superior performance across state-of-the-art techniques in estimation with either RGB video or mmWave radar. The code will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12132
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
Yang, Xiao
He, Dengbo
Wang, Jiyao
Wu, Kaishun
Computer Vision and Pattern Recognition
Remote physiological measurement gained wide attention, while it requires collecting users' privacy-sensitive information, and existing contactless measurements still rely on labeled client data. This presents challenges when we want to further update real-world deployed models with numerous user data lacking labels. To resolve these challenges, we instantiate a new protocol called Federated Unsupervised Domain Generalization (FUDG) in this work. Subsequently, the \textbf{Fed}erated \textbf{H}eterogeneous \textbf{U}nsupervised \textbf{G}eneralization (\textbf{FedHUG}) framework is proposed and consists of: (1) Minimal Bias Aggregation module dynamically adjusts aggregation weights based on prior-driven bias evaluation to cope with heterogeneous non-IID features from multiple domains. (2) The Global Distribution-aware Learning Controller parameterizes the label distribution and dynamically manipulates client-specific training strategies, thereby mitigating the server-client label distribution skew and long-tail issue. The proposal shows superior performance across state-of-the-art techniques in estimation with either RGB video or mmWave radar. The code will be released.
title FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12132