从EEG重建视觉刺激：基于GAN的脑到图像生成基线研究
原标题：Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks
AI 摘要
该研究在 THINGS-EEG2 数据集上提出一个可复现的单被试基线，用紧凑的时空卷积编码器将重复平均后的 EEG 映射到 ViT-B/32 图像特征，测试 EEG 能否在视觉嵌入空间中检索到所看刺激。三个随机种子下，模型在 200 类测试集上取得显著高于随机水平的图像召回率（1/5/10），但跨被试迁移性能骤降，且从随机初始化直接训练的条件生成器输出以噪声为主。结论支持闭集、重复平均协议下的粗粒度语义解码，但不支持忠实恢复刺激像素。
正文节选
Brain-to-Image Generation: Reconstructing Visual Stimuli from EEG using Generative Adversarial Networks Abstract Reconstructing visual stimuli from electroencephalography (EEG) is difficult because scalp measurements have high temporal but limited spatial resolution, and paired EEG–image datasets remain small relative to modern generative-model training corpora. We present a reproducible single-subject baseline on THINGS-EEG2 that first tests the more defensible question of whether EEG can retri