# PSDNorm: Test-Time Temporal Normalization for Deep Learning in Sleep Staging

arXiv: https://arxiv.org/abs/2503.04582 · HTML: https://mlsanity.com/paper/2503.04582/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 59 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG](https://mlsanity.com/paper/1703.04046/) (2017)
- [SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging](https://mlsanity.com/paper/1809.10932/) (2018)
- [U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging](https://mlsanity.com/paper/1910.11162/) (2019)
- [XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging](https://mlsanity.com/paper/2007.05492/) (2020)
- [SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification](https://mlsanity.com/paper/2105.11043/) (2021)
- [A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series](https://mlsanity.com/paper/1707.03321/) (2017)
- [SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG](https://mlsanity.com/paper/2206.01323/) (2022)
- [Neural network an1alysis of sleep stages enables efficient diagnosis of narcolepsy](https://mlsanity.com/paper/1710.02094/) (2017)
- [RobustSleepNet: Transfer learning for automated sleep staging at scale](https://mlsanity.com/paper/2101.02452/) (2021)
- [L-SeqSleepNet: Whole-cycle Long Sequence Modelling for Automatic Sleep Staging](https://mlsanity.com/paper/2301.03441/) (2023)
- [On The Effects Of Data Normalisation For Domain Adaptation On EEG Data](https://mlsanity.com/paper/2210.01081/) (2022)
- [Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment](https://mlsanity.com/paper/2407.14303/) (2024)

## Built on by (most cited first, 2 of 2)

- [Leveraging Generic Time Series Foundation Models for EEG Classification](https://mlsanity.com/paper/2510.27522/) (2025)
- [Source-Learned Reliance for Selective Test-Time Adaptation of Multimodal Time Series](https://mlsanity.com/paper/2610.07499/) (2026)

## 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.