Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces NeuroAdapt-Bench, a benchmark for evaluating test-time adaptation (TTA) methods on EEG foundation models under realistic distribution shifts, addressing the challenge of deploying these models in diverse clinical settings. The study evaluates various TTA approaches across multiple pretrained models, tasks, and datasets, revealing that standard TTA methods often degrade performance, particularly gradient-based approaches. Optimization-free methods show more stability, highlighting the need for domain-specific adaptation strategies in EEG.
Turns out, naively applying test-time adaptation to EEG foundation models can actually *hurt* performance, especially if you're using gradient-based methods.
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.