菜单

关于 🐙 GitHub
arXiv 提交日期: 2025-12-09
📄 Abstract - BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain

Understanding how the human brain represents visual concepts, and in which brain regions these representations are encoded, remains a long-standing challenge. Decades of work have advanced our understanding of visual representations, yet brain signals remain large and complex, and the space of possible visual concepts is vast. As a result, most studies remain small-scale, rely on manual inspection, focus on specific regions and properties, and rarely include systematic validation. We present a large-scale, automated framework for discovering and explaining visual representations across the human cortex. Our method comprises two main stages. First, we discover candidate interpretable patterns in fMRI activity through unsupervised, data-driven decomposition methods. Next, we explain each pattern by identifying the set of natural images that most strongly elicit it and generating a natural-language description of their shared visual meaning. To scale this process, we introduce an automated pipeline that tests multiple candidate explanations, assigns quantitative reliability scores, and selects the most consistent description for each voxel pattern. Our framework reveals thousands of interpretable patterns spanning many distinct visual concepts, including fine-grained representations previously unreported.

顶级标签: medical multi-modal model evaluation
详细标签: fmri analysis brain imaging visual representation sparse autoencoders neuroscience discovery 或 搜索:

BrainExplore:用于大规模发现和解释人类大脑视觉表征的自动化框架 / BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain


1️⃣ 一句话总结

本文提出了一个名为BrainExplore的自动化框架,它通过整合无监督数据驱动分解、预测性fMRI信号增强以及基于视觉语言模型的自动化解释流程,能够大规模、系统性地从全脑fMRI数据中发现数千个可解释的、精细粒度的视觉概念表征模式。


2️⃣ 论文创新点

1. 大规模自动化发现与解释框架

2. 融合预测性fMRI信号进行数据增强

3. 基于稀疏自编码器(SAE)的fMRI分解

4. 可扩展的自动化模式解释流程

5. 跨分解方法的集成搜索与评估框架


3️⃣ 主要结果与价值

结果亮点

实际价值


4️⃣ 术语表

源自 arXiv: 2512.08560