Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts

TL;DR

This paper systematically evaluates test-time adaptation methods for EEG foundation models under real-world distribution shifts, revealing their limitations and guiding future research.

Contribution

Introduces NeuroAdapt-Bench, a benchmark for EEG TTA, and provides a comprehensive evaluation of existing methods across diverse datasets and tasks.

Findings

Standard TTA methods show inconsistent performance and can degrade accuracy.

Gradient-based TTA approaches are particularly prone to performance degradation.

Optimization-free TTA methods are more stable and reliably improve model performance.

Abstract

Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that standard TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation. In contrast, optimization-free methods demonstrate greater stability and more reliable improvements. These findings highlight the limitations of existing TTA techniques in EEG, provide guidance for future development, and underscore the need for domain-specific adaptation strategies.