论文概要
研究领域: ML 作者: Zhenyao Cui, Siyuan Kan, Siyang Li, Ziwei Wang, Dongrui Wu 发布时间: 2026-08-19 arXiv: 2608.19134
中文摘要
准确的视觉解码可以揭示大脑如何表示视觉信息，并从神经信号如脑电图（EEG）中恢复感知内容，具有神经通信的潜力。然而，当前EEG到图像检索方法对于没有标记校准的新用户的表现远低于其受试者内对应物，限制了实际部署。为了理解这一差距，我们分析跨受试者的EEG特征，发现不同受试者保留了概念之间的相似关系，但沿着不同的坐标方向表达它们。因此，我们提出SCORE（受试者坐标恢复），一个结合恢复感知源训练与部署时坐标对齐的无目标标签框架。在训练期间，SCORE将源受试者EEG与公共图像空间对齐，并通过仅源片段模拟未见受试者恢复。在部署时，两个编码器都冻结，SCORE通过hubness校正匹配选择可靠的EEG-图像地标，并估计正交变换来恢复目标EEG坐标，无需源数据或目标标签。在两个公共基准上的200路检索中，SCORE对每个目标受试者都优于未适应基线，并实现最佳的整体准确性。它在THINGS-EEG2和Alljoined-1.6M上分别达到53.23%/83.55%和12.01%/32.16%的Top-1/Top-5，超过最强基线17.45/15.70和3.08/4.62个百分点。没有目标标签或编码器更新，SCORE使基于大脑的视觉解码更接近跨用户的鲁棒、实用、低延迟部署。
原文摘要
Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject counterparts for new users without labeled calibration, limiting real-world deployment. To understand this gap, we analyze EEG features across subjects and find that different subjects preserve similar relationships among concepts but express them along different coordinate directions. We therefore propose Subject Coordinate Recovery (SCORE), a target label-free framework combining recovery-aware source training with coordinate alignment at deployment. During training, SCORE aligns source subject EE…
— 自动采集于 2026-08-21
#论文 #arXiv #ML #小凯