Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding

TL;DR

This paper introduces MB2L, a novel framework for EEG-based visual decoding that uses biomimetic learning and contrastive objectives to improve image retrieval accuracy across subjects.

Contribution

The paper proposes a multi-level bidirectional biomimetic learning approach incorporating physiological priors and hierarchical visual features for better EEG-image alignment.

Findings

Achieves 80.5% Top-1 accuracy in zero-shot EEG-to-image retrieval.

Outperforms prior methods significantly in accuracy.

Demonstrates strong generalization across subjects.

Abstract

EEG-based visual neural decoding aims to align neural responses with visual stimuli for tasks such as image retrieval. However, limited paired data and a fundamental mismatch between high-fidelity digital images and biological visual perception - distorted by retinotopic mapping and subject-specific neuroanatomy - severely impede cross-modal alignment. To address this, we propose MB2L, a Multi-Level Bidirectional Biomimetic Learning framework that incorporates structured physiological inductive biases into representation learning. Specifically, we propose Adaptive Blur with Visual Priors to mitigate perceptual-structural mismatch by reweighting visual inputs according to retinotopic priors. We further propose Biomimetic Visual Feature Extraction to learn multi-level visual representations consistent with hierarchical cortical processing, enhancing subject-invariant encoding. These modules are jointly optimized via Multi-level Bidirectional Contrastive Learning, which aligns EEG and visual features in a shared semantic space through bidirectional contrastive objectives. Experiments show MB2L achieves 80.5% Top-1 and 97.6% Top-5 accuracy on zero-shot EEG-to-image retrieval, significantly outperforming prior methods and demonstrating strong generalization across subjects and experimental settings.