FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
Not on the map. Why?
Abstract (arXiv)
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 Federated Heterogeneous Unsupervised Generalization (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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 78 references that are in the map. First posted on arXiv 14 Oct 2025.
Builds on
44 of 78 references.
References · 44
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020The Future of Digital Health with Federated Learningcited by 633
- 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
- 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
- 2018DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networkscited by 154
- 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
- 2019RhythmNet: End-to-end Heart Rate Estimation from Face via Spatial-temporal Representationcited by 105
- 2020Federated Unsupervised Representation Learningcited by 93
32 more
- 2019Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancementcited by 87
- 2020Video-based Remote Physiological Measurement via Cross-verified Feature Disentanglingcited by 79
- 2022Divergence-aware Federated Self-Supervised Learningcited by 73
- 2021The Way to my Heart is through Contrastive Learning: Remote Photoplethysmography from Unlabelled Videocited by 66
- 2020PulseGAN: Learning to generate realistic pulse waveforms in remote photoplethysmographycited by 60
- 2018VIPL-HR: A Multi-modal Database for Pulse Estimation from Less-constrained Face Videocited by 58
- 2023MMPD: Multi-Domain Mobile Video Physiology Datasetcited by 57
- 2022Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrastcited by 48
- 2023PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformercited by 48
- 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
- 2023Non-Contrastive Unsupervised Learning of Physiological Signals from Videocited by 37
- 2023Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal Contrastcited by 34
- 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
- 2022SCAMPS: Synthetics for Camera Measurement of Physiological Signalscited by 28
- 2023Image Enhancement for Remote Photoplethysmography in a Low-Light Environmentcited by 23
- 2024GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computingcited by 22
- 2025Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysiscited by 18
- 2024SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learningcited by 14
- 2024Advancing Generalizable Remote Physiological Measurement through the Integration of Explicit and Implicit Prior Knowledgecited by 13
- 2024Rethinking the Representation in Federated Unsupervised Learning with Non-IID Datacited by 13
- 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 12
- 2024PhysMLE: Generalizable and Priors-Inclusive Multi-task Remote Physiological Measurementcited by 10
- 2024Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Drivingcited by 9
- 2025CardiacMamba: A Multimodal RGB-RF Fusion Framework with State Space Models for Remote Physiological Measurementcited by 8
- 2022Federated Remote Physiological Measurement with Imperfect Datacited by 7
- 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7
- 2025PhysDrive: A Multimodal Remote Physiological Measurement Dataset for In-vehicle Driver Monitoringcited by 7
- 2025Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalizationcited by 4
- 2024Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computingcited by 3
- 2024Revisiting Interactions of Multiple Driver States in Heterogenous Population and Cognitive Taskscited by 3
- 2025Not Only Consistency: Enhance Test-Time Adaptation with Spatio-temporal Inconsistency for Remote Physiological Measurementcited by 3
- 2025Towards Generalizable Drowsiness Monitoring with Physiological Sensors: A Preliminary Studycited by 2
Built on by
Not cited yet.