Leveraging Generic Time Series Foundation Models for EEG Classification

TL;DR

This paper demonstrates that general-purpose time series foundation models, pretrained on diverse or synthetic data, outperform specialized EEG models in classification tasks, indicating broad transferability to EEG analysis.

Contribution

It shows that generic time series foundation models can be effectively applied to EEG tasks, outperforming existing EEG-specific models, even when pretrained on non-neural data.

Findings

Both pretraining regimes outperform EEGNet and CBraMod.

Pretraining on synthetic data is nearly as effective as on real-world data.

Cross-domain pretrained models transfer well to EEG classification.

Abstract

Foundation models for time series are emerging as powerful general-purpose backbones, yet their potential for domain-specific biomedical signals such as electroencephalography (EEG) remains rather unexplored. In this work, we investigate the applicability a recently proposed time series classification foundation model, to a different EEG tasks such as motor imagery classification and sleep stage prediction. We test two pretraining regimes: (a) pretraining on heterogeneous real-world time series from multiple domains, and (b) pretraining on purely synthetic data. We find that both variants yield strong performance, consistently outperforming EEGNet, a widely used convolutional baseline, and CBraMod, the most recent EEG-specific foundation model. These results suggest that generalist time series foundation models, even when pretrained on data of non-neural origin or on synthetic signals, can transfer effectively to EEG. Our findings highlight the promise of leveraging cross-domain pretrained models for brain signal analysis, suggesting that EEG may benefit from advances in the broader time series literature.