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

TL;DR

This work introduces the concept of Neural Visibility and accordingly proposes the EEG-Visible Layer Selection Strategy, aligning EEG signals with intermediate visual layers to minimize this mismatch and proposes a novel Hierarchically Complementary Fusion (HCF) framework that jointly integrates visual representations from different hierarchical levels.

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.

Figures (5)

• Figure 1: Overview of the proposed EEG-visible alignment framework for brain–vision matching.
• Figure 2: Layer-wise Performance Across Architectures and Pooling Strategies
• Figure 3: Layer Pairwise Fusion Analysis (ViT)
• Figure 4: Retrieved Samples
• Figure 5: Visualization of spatial frequency components and their impact on EEG–image retrieval performance.