NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment

TL;DR

NeuroBridge is a novel self-supervised EEG-to-image decoding framework that uses cognitive priors and bidirectional semantic alignment to improve neural visual decoding accuracy and robustness.

Contribution

It introduces a bio-inspired architecture combining cognitive prior augmentation with shared semantic projection for enhanced cross-modal alignment.

Findings

Achieves 12.3% top-1 accuracy improvement in intra-subject decoding.

Reaches 89.9% top-5 accuracy in zero-shot retrieval.

Demonstrates robustness and scalability across different experimental settings.

Abstract

Visual neural decoding seeks to reconstruct or infer perceived visual stimuli from brain activity patterns, providing critical insights into human cognition and enabling transformative applications in brain-computer interfaces and artificial intelligence. Current approaches, however, remain constrained by the scarcity of high-quality stimulus-brain response pairs and the inherent semantic mismatch between neural representations and visual content. Inspired by perceptual variability and co-adaptive strategy of the biological systems, we propose a novel self-supervised architecture, named NeuroBridge, which integrates Cognitive Prior Augmentation (CPA) with Shared Semantic Projector (SSP) to promote effective cross-modality alignment. Specifically, CPA simulates perceptual variability by applying asymmetric, modality-specific transformations to both EEG signals and images, enhancing semantic diversity. Unlike previous approaches, SSP establishes a bidirectional alignment process through a co-adaptive strategy, which mutually aligns features from two modalities into a shared semantic space for effective cross-modal learning. NeuroBridge surpasses previous state-of-the-art methods under both intra-subject and inter-subject settings. In the intra-subject scenario, it achieves the improvements of 12.3% in top-1 accuracy and 10.2% in top-5 accuracy, reaching 63.2% and 89.9% respectively on a 200-way zero-shot retrieval task. Extensive experiments demonstrate the effectiveness, robustness, and scalability of the proposed framework for neural visual decoding.