Rethinking Self-Training Based Cross-Subject Domain Adaptation for SSVEP Classification

TL;DR

This paper introduces a novel cross-subject domain adaptation framework for SSVEP classification in BCIs, combining self-training, adversarial learning, and contrastive modules to improve accuracy across subjects.

Contribution

It proposes a new method integrating FBEA, PTAL, DEST, and TFA-CL to enhance cross-subject SSVEP decoding performance.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Effectively reduces signal variability across subjects.

Improves robustness with varying signal lengths.

Abstract

Steady-state visually evoked potentials (SSVEP)-based brain-computer interfaces (BCIs) are widely used due to their high signal-to-noise ratio and user-friendliness. Accurate decoding of SSVEP signals is crucial for interpreting user intentions in BCI applications. However, signal variability across subjects and the costly user-specific annotation limit recognition performance. Therefore, we propose a novel cross-subject domain adaptation method built upon the self-training paradigm. Specifically, a Filter-Bank Euclidean Alignment (FBEA) strategy is designed to exploit frequency information from SSVEP filter banks. Then, we propose a Cross-Subject Self-Training (CSST) framework consisting of two stages: Pre-Training with Adversarial Learning (PTAL), which aligns the source and target distributions, and Dual-Ensemble Self-Training (DEST), which refines pseudo-label quality. Moreover, we introduce a Time-Frequency Augmented Contrastive Learning (TFA-CL) module to enhance feature discriminability across multiple augmented views. Extensive experiments on the Benchmark and BETA datasets demonstrate that our approach achieves state-of-the-art performance across varying signal lengths, highlighting its superiority.