CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Information

TL;DR

CognitionCapturer is a novel framework that decodes visual stimuli from EEG signals by leveraging multimodal data and a diffusion prior, achieving high-fidelity reconstructions without fine-tuning generative models.

Contribution

It introduces a unified multimodal approach with modality-specific encoders and a diffusion prior to improve visual stimulus reconstruction from EEG signals.

Findings

Outperforms state-of-the-art methods quantitatively.

Produces high semantic and structural fidelity in reconstructed images.

Extensible to incorporate additional modalities.

Abstract

Electroencephalogram (EEG) signals have attracted significant attention from researchers due to their non-invasive nature and high temporal sensitivity in decoding visual stimuli. However, most recent studies have focused solely on the relationship between EEG and image data pairs, neglecting the valuable ``beyond-image-modality" information embedded in EEG signals. This results in the loss of critical multimodal information in EEG. To address this limitation, we propose CognitionCapturer, a unified framework that fully leverages multimodal data to represent EEG signals. Specifically, CognitionCapturer trains Modality Expert Encoders for each modality to extract cross-modal information from the EEG modality. Then, it introduces a diffusion prior to map the EEG embedding space to the CLIP embedding space, followed by using a pretrained generative model, the proposed framework can reconstruct visual stimuli with high semantic and structural fidelity. Notably, the framework does not require any fine-tuning of the generative models and can be extended to incorporate more modalities. Through extensive experiments, we demonstrate that CognitionCapturer outperforms state-of-the-art methods both qualitatively and quantitatively. Code: https://github.com/XiaoZhangYES/CognitionCapturer.