Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.04680 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911652393254912 |
|---|---|
| author | Liu, Jingtao Gong, Peiliang Zheng, Chuhang Liu, Yiheng Zhu, Qi |
| author_facet | Liu, Jingtao Gong, Peiliang Zheng, Chuhang Liu, Yiheng Zhu, Qi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04680 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding Liu, Jingtao Gong, Peiliang Zheng, Chuhang Liu, Yiheng Zhu, Qi Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Multi-Level Bidirectional Biomimetic Learning for EEG-Based Visual Decoding |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.04680 |