EEGiT：让视觉 Transformer 理解脑电信号
EEGiT: Teaching Vision Transformers to Understand the EEG signal
把时序脑电信号重排成类图像 patch 并插值对齐空间拓扑，从而直接复用预训练 ViT 的视觉先验——这套「非图像模态转 patch 后套用 ViT」的流程可迁移到其他低数据模态（如传感器、生理信号）的表征学习与检索。
原文依据 converts sequential EEG signals into image-like EEG patches and enables the direct use of a pretrained Vision Transformer (ViT) as the EEG encoder
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从脑电信号中解码视觉刺激是迈向实用脑机接口的关键一步。然而，该任务需要大规模、高质量的脑电-图像配对数据集。与丰富的图像数据相比，有限的脑电记录制约了解码模型的性能。为应对这一挑战，我们提出 EEGiT 框架，将时序脑电信号转换为类图像的脑电 patch，从而可以直接使用预训练的视觉 Transformer（ViT）作为脑电编码器。为保留脑区的空间拓扑结构并减小通道间的分布差异，我们依据解剖结构对脑电电极进行分组，并沿空间维度施加线性插值。随后我们对脑电信号重采样，使脑电 patch 的结构与 ViT 中图像 patch 的结构对齐。这一设计促进了从大规模图像数据集中学到的视觉先验向脑电表征学习的有效迁移。在 THINGS-EEG 和 EEG-3D 数据集上的实验表明，微调预训练 ViT 可提升脑电到图像的检索以及基于脑电的视觉分类性能，同时保持鲁棒性和较强的跨被试泛化能力。这些结果展示了利用强大视觉模型缓解脑电解码中数据稀缺问题的一条有前景的方向。
英文原文摘要 1352 字符
Decoding visual stimuli from electroencephalography (EEG) signals is a crucial step toward practical brain-computer interfaces (BCIs). However, this task requires large-scale and high-quality EEG-image paired datasets. Compared with abundant image data, the limited EEG recordings restrict the decoding models' performance. To address this challenge, we propose EEGiT, a framework that converts sequential EEG signals into image-like EEG patches and enables the direct use of a pretrained Vision Transformer (ViT) as the EEG encoder. To preserve the spatial topology of brain regions and minimize distributional differences across channels, we group EEG electrodes according to anatomical structures and apply linear interpolation along the spatial dimension. We then resample the EEG signals to align the structure of EEG patches with that of image patches in ViT. This design encourages effective transfer of visual priors learned from large-scale image datasets to EEG representation learning. Experiments on the THINGS-EEG and EEG-3D datasets show that fine-tuning pretrained ViTs improves EEG-to-image retrieval and EEG-based visual classification, while maintaining robustness and strong cross-subject generalization. These results demonstrate a promising direction for leveraging powerful vision models to mitigate data scarcity in EEG decoding.