MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Zexuan, Liu, Sichao, Lu, Runhao, Qi, Huichao, Woolgar, Alexandra, Wang, Xi Vincent, Wang, Lihui
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911713286160384
author Chen, Zexuan
Liu, Sichao
Lu, Runhao
Qi, Huichao
Woolgar, Alexandra
Wang, Xi Vincent
Wang, Lihui
author_facet Chen, Zexuan
Liu, Sichao
Lu, Runhao
Qi, Huichao
Woolgar, Alexandra
Wang, Xi Vincent
Wang, Lihui
contents Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. We introduce a tri-modal contrastive framework for EEG-based visual decoding that aligns EEG, visual, and textual representations within a unified latent space. Our approach follows a two-stage design. First, we pre-train an EEG encoder via masked reconstruction on unlabeled trials, learning spatio-temporal regularities that transfer robustly to downstream tasks. Second, we jointly align EEG, image, and LLM-generated textual descriptions through contrastive learning, where text supervision acts as a semantic regularizer that injects linguistic structure into the shared space without overwhelming the primary EEG-image signal. The encoder integrates subject-specific adaptation, graph-attention over channels, and temporal-spatial convolutional embeddings. On the Things-EEG2 200-way zero-shot benchmark, our framework achieves 54.1% Top-1 and 83.4% Top-5 accuracy, substantially exceeding the strongest prior baseline (32.4% / 64.0%), with paired Wilcoxon tests confirming significance (p < 0.01) over all in-subject baselines. We validate generalization on Things-MEG. Analysis reveals that compact embedding geometries (CN-CLIP) outperform much larger backbones, and that decoding aligns with established neurophysiology of visual processing. This work is a critical step towards robust, semantically-grounded visual decoding from non-invasive temporal neural signals. The source code is publicly available in https://github.com/anon-eeg/eeg_image_decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24523
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
Chen, Zexuan
Liu, Sichao
Lu, Runhao
Qi, Huichao
Woolgar, Alexandra
Wang, Xi Vincent
Wang, Lihui
Machine Learning
Computation and Language
Neurons and Cognition
Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. We introduce a tri-modal contrastive framework for EEG-based visual decoding that aligns EEG, visual, and textual representations within a unified latent space. Our approach follows a two-stage design. First, we pre-train an EEG encoder via masked reconstruction on unlabeled trials, learning spatio-temporal regularities that transfer robustly to downstream tasks. Second, we jointly align EEG, image, and LLM-generated textual descriptions through contrastive learning, where text supervision acts as a semantic regularizer that injects linguistic structure into the shared space without overwhelming the primary EEG-image signal. The encoder integrates subject-specific adaptation, graph-attention over channels, and temporal-spatial convolutional embeddings. On the Things-EEG2 200-way zero-shot benchmark, our framework achieves 54.1% Top-1 and 83.4% Top-5 accuracy, substantially exceeding the strongest prior baseline (32.4% / 64.0%), with paired Wilcoxon tests confirming significance (p < 0.01) over all in-subject baselines. We validate generalization on Things-MEG. Analysis reveals that compact embedding geometries (CN-CLIP) outperform much larger backbones, and that decoding aligns with established neurophysiology of visual processing. This work is a critical step towards robust, semantically-grounded visual decoding from non-invasive temporal neural signals. The source code is publicly available in https://github.com/anon-eeg/eeg_image_decoding.
title MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
topic Machine Learning
Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2605.24523