DenoFlow: Flow Matching for SSVEP Denoising under Real Physiological Artifacts

Computer Science > Machine Learning arXiv:2610.08817 (cs) [Submitted on 24 Sep 2026] Title: DenoFlow: Flow Matching for SSVEP Denoising under Real Physiological Artifacts Authors: Zhentao He, Ziwei Wang, Dongrui Wu.

计算机科学 > 机器学习 arXiv:2610.08817 (cs) [提交于 2026 年 9 月 24 日] 标题：DenoFlow：用于真实生理伪影下 SSVEP 去噪的流匹配方法 作者：Zhentao He, Ziwei Wang, Dongrui Wu。

Abstract: Electroencephalography (EEG)-based brain-computer interfaces (BCIs), particularly steady-state visual evoked potential (SSVEP) systems, are highly vulnerable to noise and artifacts, which severely degrade decoding accuracy. Although recent denoising approaches have shown promise, they are fitted without paired ground truth, can settle on reproducing their input, and are optimized on waveform distance alone, which says nothing about whether the output stays decodable.

摘要：基于脑电图（EEG）的脑机接口（BCI），特别是稳态视觉诱发电位（SSVEP）系统，极易受到噪声和伪影的影响，这严重降低了解码精度。尽管近期的去噪方法已显示出前景，但它们在拟合时缺乏配对的真实数据（ground truth），可能倾向于简单地复现输入，且仅针对波形距离进行优化，这无法保证输出结果是否仍具有可解码性。

To address these issues, we propose DenoFlow, which casts SSVEP denoising as transport: instead of learning a direct map from a contaminated trial to a clean one, a field network regresses the velocity of the straight path between them, following the rectified-flow formulation, and denoising integrates that field forward from the observation. The field network is an encoder-decoder that sees the contaminated trial at every layer and the path position at its bottleneck, and a classifier trained alongside it supervises the integrated output.

为了解决这些问题，我们提出了 DenoFlow，它将 SSVEP 去噪视为一种传输过程：不再学习从受污染试验到干净试验的直接映射，而是遵循修正流（rectified-flow）公式，由一个场网络回归两者之间直线路径的速度，并通过从观测值开始向前积分该场来实现去噪。该场网络是一个编码器-解码器结构，在每一层都能看到受污染的试验，并在瓶颈处获取路径位置，同时通过与其共同训练的分类器来监督积分后的输出。

Because the observation itself is both the conditioning input and the starting point of the integration, the model never generates a trial from noise, and training reduces to regression, removing the adversarial min-max game. To obtain paired data on datasets with no ground truth, we injected physiological artifacts of the recorded electromyography (EMG) and electrooculography (EOG) signals under a controlled signal-to-noise target.

由于观测值本身既是条件输入，也是积分的起点，模型从不从噪声中生成试验，训练过程简化为回归问题，从而消除了对抗性的极小极大博弈。为了在没有真实数据的测试集上获得配对数据，我们在受控的信噪比目标下，注入了记录到的肌电图（EMG）和眼电图（EOG）信号的生理伪影。

Experiments on two public SSVEP datasets with five popular SSVEP decoders showed that DenoFlow outperformed seven baseline denoising models on both signal fidelity and downstream decoding accuracy. Code is available at this https URL.

在两个公开的 SSVEP 数据集上，使用五种主流 SSVEP 解码器进行的实验表明，DenoFlow 在信号保真度和下游解码精度方面均优于七种基准去噪模型。代码可在该 URL 获取。