A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding

TL;DR

This paper introduces VCFlow, a hierarchical brain decoding framework inspired by the visual system, enabling rapid, subject-agnostic reconstruction of visual experiences from fMRI with minimal accuracy loss.

Contribution

The paper presents VCFlow, a novel hierarchical architecture with contrastive learning for fast, subject-agnostic visual decoding from fMRI data, reducing training time and computational costs.

Findings

VCFlow achieves 93% of the accuracy of subject-specific models.

Reconstructs videos in 10 seconds without retraining.

Requires only 7% of the data needed by traditional methods.

Abstract

Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a novel hierarchical decoding framework that explicitly models the ventral-dorsal architecture of the human visual system to learn multi-dimensional representations. By disentangling and leveraging features from early visual cortex, ventral, and dorsal streams, VCFlow captures diverse and complementary cognitive information essential for visual reconstruction. Furthermore, we introduce a feature-level contrastive learning strategy to enhance the extraction of subject-invariant semantic representations, thereby enhancing subject-agnostic applicability to previously unseen subjects. Unlike conventional pipelines that need more than 12 hours of per-subject data and heavy computation, VCFlow sacrifices only 7\% accuracy on average yet generates each reconstructed video in 10 seconds without any retraining, offering a fast and clinically scalable solution. The source code will be released upon acceptance of the paper.