PSDNorm: Test-Time Temporal Normalization for Deep Learning in Sleep Staging
Not on the map. Why?
Abstract (arXiv)
Distribution shift poses a significant challenge in machine learning, particularly in biomedical applications using data collected across different subjects, institutions, and recording devices, such as sleep data. While existing normalization layers, BatchNorm, LayerNorm and InstanceNorm, help mitigate distribution shifts, when applied over the time dimension they ignore the dependencies and auto-correlation inherent to the vector coefficients they normalize. In this paper, we propose PSDNorm that leverages Monge mapping and temporal context to normalize feature maps in deep learning models for signals. Evaluations with architectures based on U-Net or transformer backbones trained on 10K subjects across 10 datasets, show that PSDNorm achieves state-of-the-art performance on unseen left-out datasets while being more robust to data scarcity.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 59 references that are in the map. First posted on arXiv 6 Mar 2025.
Builds on
22 of 59 references.
References · 22
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2016Layer Normalizationcited by 5,579
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
- 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
- 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
- 2021Generalized Source-free Domain Adaptationcited by 175
- 2017DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEGcited by 154
- 2018SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Stagingcited by 90
10 more
- 2019U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Stagingcited by 87
- 2020XSleepNet: Multi-View Sequential Model for Automatic Sleep Stagingcited by 87
- 2021SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantificationcited by 83
- 2017A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time seriescited by 58
- 2022SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEGcited by 53
- 2017Neural network an1alysis of sleep stages enables efficient diagnosis of narcolepsycited by 39
- 2021RobustSleepNet: Transfer learning for automated sleep staging at scalecited by 24
- 2023L-SeqSleepNet: Whole-cycle Long Sequence Modelling for Automatic Sleep Stagingcited by 21
- 2022On The Effects Of Data Normalisation For Domain Adaptation On EEG Datacited by 13
- 2024Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignmentcited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.