Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gong, Peiliang, Zhang, Han, Jiang, Zhen, Liu, Chenyu, Jia, Ziyu, Zhou, Xinliang, Zhang, Daoqiang, Li, Xiaoli
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911639622647808
author Gong, Peiliang
Zhang, Han
Jiang, Zhen
Liu, Chenyu
Jia, Ziyu
Zhou, Xinliang
Zhang, Daoqiang
Li, Xiaoli
author_facet Gong, Peiliang
Zhang, Han
Jiang, Zhen
Liu, Chenyu
Jia, Ziyu
Zhou, Xinliang
Zhang, Daoqiang
Li, Xiaoli
contents Source-free domain adaptation (SFDA) provides a practical solution to cross-subject EEG decoding by adapting source-pretrained models to unlabeled target domains without accessing source data. However, existing SFDA methods rely solely on the limited internal knowledge of source-pretrained models, leading to inferior cross-domain generalization and unreliable pseudo-labels. Although EEG Foundation Models (FMs) pretrained on large-scale data exhibit strong generalizability, their potential in SFDA remains largely unexplored. To this end, we propose FUSED, a Foundation-guided Source-free EEG Decoding framework that integrates a large-scale FM with a compact Specialist Model (SM) via dual-branch co-adaptation. Specifically, we introduce a Co-adaptation mechanism equipping both branches with linear and prototype views, enabling cross-branch pseudo-label generation. Additionally, we design a Consensus Filtering Mechanism that exploits the FM's inherent stability to identify high-quality samples, along with a Two-Stage Pseudo-Label Refinement scheme to suppress error accumulation through cross-branch arbitration. Finally, we calibrate the FM's decision boundaries via mutual information maximization with the SM, followed by knowledge distillation from FM to SM, forming a principled calibrate-then-distill pipeline. To our knowledge, FUSED is the first work to leverage EEG FMs within the SFDA framework for cross-subject EEG decoding. Extensive experiments across three EEG paradigms, including motor imagery, emotion recognition, and SSVEP, demonstrate consistent state-of-the-art performance, validating the effectiveness of foundation-guided synergy for robust and privacy-preserving EEG decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00857
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding
Gong, Peiliang
Zhang, Han
Jiang, Zhen
Liu, Chenyu
Jia, Ziyu
Zhou, Xinliang
Zhang, Daoqiang
Li, Xiaoli
Signal Processing
Artificial Intelligence
Machine Learning
Neurons and Cognition
Source-free domain adaptation (SFDA) provides a practical solution to cross-subject EEG decoding by adapting source-pretrained models to unlabeled target domains without accessing source data. However, existing SFDA methods rely solely on the limited internal knowledge of source-pretrained models, leading to inferior cross-domain generalization and unreliable pseudo-labels. Although EEG Foundation Models (FMs) pretrained on large-scale data exhibit strong generalizability, their potential in SFDA remains largely unexplored. To this end, we propose FUSED, a Foundation-guided Source-free EEG Decoding framework that integrates a large-scale FM with a compact Specialist Model (SM) via dual-branch co-adaptation. Specifically, we introduce a Co-adaptation mechanism equipping both branches with linear and prototype views, enabling cross-branch pseudo-label generation. Additionally, we design a Consensus Filtering Mechanism that exploits the FM's inherent stability to identify high-quality samples, along with a Two-Stage Pseudo-Label Refinement scheme to suppress error accumulation through cross-branch arbitration. Finally, we calibrate the FM's decision boundaries via mutual information maximization with the SM, followed by knowledge distillation from FM to SM, forming a principled calibrate-then-distill pipeline. To our knowledge, FUSED is the first work to leverage EEG FMs within the SFDA framework for cross-subject EEG decoding. Extensive experiments across three EEG paradigms, including motor imagery, emotion recognition, and SSVEP, demonstrate consistent state-of-the-art performance, validating the effectiveness of foundation-guided synergy for robust and privacy-preserving EEG decoding.
title Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding
topic Signal Processing
Artificial Intelligence
Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2605.00857