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

arXiv: https://arxiv.org/abs/2601.21203 · HTML: https://mlsanity.com/paper/2601.21203/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Self-supervised Learning for Electroencephalogram: A Systematic Survey](https://mlsanity.com/paper/2401.05446/) (2024)
- [BETA: A Large Benchmark Database Toward SSVEP-BCI Application](https://mlsanity.com/paper/1911.13045/) (2019)
- [Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces](https://mlsanity.com/paper/2502.09203/) (2025)
- [Transfer Learning of an Ensemble of DNNs for SSVEP BCI Spellers without User-Specific Training](https://mlsanity.com/paper/2209.01511/) (2022)
- [Source-Free Domain Adaptation for SSVEP-based Brain-Computer Interfaces](https://mlsanity.com/paper/2305.17403/) (2023)

## Abstract (arXiv)

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.