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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jingyu, Wang, Haonan, Zhang, Qixiang, Li, Xiaomeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910030828142592
author Lu, Jingyu
Wang, Haonan
Zhang, Qixiang
Li, Xiaomeng
author_facet Lu, Jingyu
Wang, Haonan
Zhang, Qixiang
Li, Xiaomeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_02565
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
Lu, Jingyu
Wang, Haonan
Zhang, Qixiang
Li, Xiaomeng
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title A Cognitive Process-Inspired Architecture for Subject-Agnostic Brain Visual Decoding
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.02565