Aligning What EEG Can See: Structural Representations for Brain-Vision Matching

TL;DR

This paper introduces a novel approach for EEG-based visual decoding that aligns brain signals with intermediate visual layers and integrates hierarchical visual representations, significantly improving accuracy and robustness.

Contribution

It proposes the Neural Visibility concept, the EEG-Visible Layer Selection Strategy, and the Hierarchically Complementary Fusion framework, advancing EEG-visual alignment methods.

Findings

Achieved 84.6% accuracy on zero-shot visual decoding.

Improved performance by up to 129.8% over EEG baselines.

Demonstrated robustness and generalizability across datasets.

Abstract

Visual decoding from electroencephalography (EEG) has emerged as a highly promising avenue for non-invasive brain-computer interfaces (BCIs). Existing EEG-based decoding methods predominantly align brain signals with the final-layer semantic embeddings of deep visual models. However, relying on these highly abstracted embeddings inevitably leads to severe cross-modal information mismatch. In this work, we introduce the concept of Neural Visibility and accordingly propose the EEG-Visible Layer Selection Strategy, aligning EEG signals with intermediate visual layers to minimize this mismatch. Furthermore, to accommodate the multi-stage nature of human visual processing, we propose a novel Hierarchically Complementary Fusion (HCF) framework that jointly integrates visual representations from different hierarchical levels. Extensive experiments demonstrate that our method achieves state-of-the-art performance, reaching an 84.6% accuracy (+21.4%) on zero-shot visual decoding on the THINGS-EEG dataset. Moreover, our method achieves up to a 129.8% performance gain across diverse EEG baselines, demonstrating its robust generalizability.