# Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning

arXiv: https://arxiv.org/abs/2605.06724 · HTML: https://mlsanity.com/paper/2605.06724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 13 of 13)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits](https://mlsanity.com/paper/1312.7308/) (2013)
- [Zero-Shot Noise2Noise: Efficient Image Denoising without any Data](https://mlsanity.com/paper/2303.11253/) (2023)
- [Speech Denoising Without Clean Training Data: A Noise2Noise Approach](https://mlsanity.com/paper/2104.03838/) (2021)
- [A novel convolutional neural network model to remove muscle artifacts from EEG](https://mlsanity.com/paper/2010.11709/) (2020)
- [EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer](https://mlsanity.com/paper/2109.04235/) (2021)
- [IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal](https://mlsanity.com/paper/2111.10026/) (2021)
- [In-ear EEG biometrics for feasible and readily collectable real-world person authentication](https://mlsanity.com/paper/1705.03742/) (2017)
- [Machine Intelligence on the Edge: Interpretable Cardiac Pattern Localisation Using Reinforcement Learning](https://mlsanity.com/paper/2508.21652/) (2025)

## Abstract (arXiv)

Denoising electroencephalogram (EEG) is an inherently challenging task, since neural activity is not only subtle but also inseparable from spectrally overlapping noise artifacts. Today, effective EEG denoising is more important than ever, given the rapid adoption of wearables across various applications. Deep learning methods have shown promising results in decomposition-free denoising that handles the time-varying pervasive EEG artifacts. However, training highly expressive neural networks requires artifact-free EEG, which is inherently unobtainable. To address this, we propose Intelligent Partitioning for Self-supervised Denoising (iPSD). Our method eliminates the need for clean references by learning to partition an input EEG segment into independent noisy realizations with the same underlying signal. This enables self-supervision of deep learning denoisers, even in zero-shot settings where only a single EEG segment to be denoised is available. We validate iPSD through extensive experiments, including validations on wearable EEG from in-ear sensors. The results show that iPSD achieves state-of-the-art performance, most notably under extremely low signal-to-noise ratios (down to -10 dB) and challenging artifacts (e.g., EMG), with spectral fidelity orders of magnitude higher than competitive baselines.