ZEBRA无需额外数据，实现跨被试的脑视觉解码零样本泛化。
ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
- 通过对抗训练分离脑影像中的个体特异与语义特征
- 在未见被试上性能接近微调模型，超越零样本基线
- 适合神经科学与脑机接口研究者快速部署通用解码系统
近年来神经解码进展使从脑活动重建视觉体验成为可能，将fMRI-to-image重建定位为神经科学与计算机视觉之间的桥梁。然而，当前方法多依赖个体特定模型或需个体微调，限制了可扩展性与实际应用。本文提出ZEBRA，首个无需个体适应的零样本脑视觉解码框架。其核心思想是将fMRI表征分解为个体相关与语义相关成分。通过对抗训练，方法显式解耦这些成分，提取出与个体无关、仅保留语义信息的表示。该解耦使ZEBRA可在无额外fMRI数据或重训练的情况下泛化至未见被试。大量实验表明，ZEBRA显著优于零样本基线，在多个指标上达到与完全微调模型相当的性能。本工作为通用神经解码提供了可扩展且实用的一步。代码与模型权重见：https://github.com/xmed-lab/ZEBRA。
原文摘要 · Abstract (English)
Recent advances in neural decoding have enabled the reconstruction of visual experiences from brain activity, positioning fMRI-to-image reconstruction as a promising bridge between neuroscience and computer vision. However, current methods predominantly rely on subject-specific models or require subject-specific fine-tuning, limiting their scalability and real-world applicability. In this work, we introduce ZEBRA, the first zero-shot brain visual decoding framework that eliminates the need for subject-specific adaptation. ZEBRA is built on the key insight that fMRI representations can be decomposed into subject-related and semantic-related components. By leveraging adversarial training, our method explicitly disentangles these components to isolate subject-invariant, semantic-specific representations. This disentanglement allows ZEBRA to generalize to unseen subjects without any additional fMRI data or retraining. Extensive experiments show that ZEBRA significantly outperforms zero-shot baselines and achieves performance comparable to fully finetuned models on several metrics. Our work represents a scalable and practical step toward universal neural decoding. Code and model weights are available at: https://github.com/xmed-lab/ZEBRA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。