English

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

Computer Vision and Pattern Recognition 2026-05-07 v1 Artificial Intelligence

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.

Keywords

Cite

@article{arxiv.2605.04680,
  title  = {Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding},
  author = {Jingtao Liu and Peiliang Gong and Chuhang Zheng and Yiheng Liu and Qi Zhu},
  journal= {arXiv preprint arXiv:2605.04680},
  year   = {2026}
}

Comments

20 pages, 13 figures, 15 tables

R2 v1 2026-07-01T12:52:25.715Z