Interpretable EEG-to-Image Generation with Semantic Prompts

TL;DR

This paper introduces a novel EEG-to-image decoding framework that uses semantic prompts from language models to improve interpretability and accuracy in visual reconstruction from brain signals.

Contribution

The study presents a new method that aligns EEG signals with semantic captions to generate images, bypassing direct EEG-to-image mapping and enhancing interpretability.

Findings

Achieved state-of-the-art visual decoding accuracy on EEG data.

Revealed semantic topography across the scalp via saliency maps.

Demonstrated alignment with neurocognitive pathways through interpretability analyses.

Abstract

Decoding visual experience from brain signals offers exciting possibilities for neuroscience and interpretable AI. While EEG is accessible and temporally precise, its limitations in spatial detail hinder image reconstruction. Our model bypasses direct EEG-to-image generation by aligning EEG signals with multilevel semantic captions -- ranging from object-level to abstract themes -- generated by a large language model. A transformer-based EEG encoder maps brain activity to these captions through contrastive learning. During inference, caption embeddings retrieved via projection heads condition a pretrained latent diffusion model for image generation. This text-mediated framework yields state-of-the-art visual decoding on the EEGCVPR dataset, with interpretable alignment to known neurocognitive pathways. Dominant EEG-caption associations reflected the importance of different semantic levels extracted from perceived images. Saliency maps and t-SNE projections reveal semantic topography across the scalp. Our model demonstrates how structured semantic mediation enables cognitively aligned visual decoding from EEG.