Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks

Decoding of visual stimuli from noninvasive neuroimaging techniques such as functional magnetic resonance (fMRI) has advanced rapidly in the last years; yet, most high-performing brain decoding models rely on complicated, non-interpretable latent spaces. In this study we present an interpretable brain decoding framework that inserts a semantic bottleneck into BrainDiffuser, a well established, simple and linear decoding pipeline. We firstly produce a 214 dimensional binary interpretable space L for images, in which each dimension answers to a specific question about the image (e.g., "Is there a person?",