Neuroscience-inspired Staged Representation Learning with Disentangled Coarse- and Fine-Grained Semantics for EEG Visual Decoding

2026-05-16

AI Summary

Existing EEG-based visual decoding approaches often overlook the staged and hierarchical nature of human visual processing, limiting their ability to faithfully reconstruct visual content. Inspired by neuroscience, this work proposes a staged representation learning framework that sequentially models low-level visual features and high-level semantics. It introduces a dual-granularity semantic disentanglement mechanism to separate coarse-grained categorical information from fine-grained image semantics and designs a semantic latent channel to expand the channel-wise semantic representation space, enabling structured semantic abstraction and cross-modal alignment. Evaluated on the THINGS-EEG benchmark, the method achieves state-of-the-art performance in both subject-dependent and subject-independent zero-shot settings for visual decoding and image retrieval, demonstrating the efficacy of staged modeling and semantic disentanglement.

Abstract

Decoding visual information from electroencephalography (EEG) signals remains a fundamental challenge in brain-computer interfaces and medical rehabilitation. Existing EEG visual decoding methods mainly focus on learning a single global EEG embedding for cross-modal alignment, but they largely overlook the staged and hierarchical characteristics of human visual processing. To address this limitation, we propose a neuroscience-inspired staged representation learning framework that reformulates EEG visual decoding as a stage-specific representation decomposition problem. The proposed framework organizes EEG representation learning into three complementary phases: low-level visual representation learning, high-level semantic representation learning, and integrative information fusion. To strengthen semantic modeling, we further introduce a multimodal dual-level semantic learning mechanism that separates coarse label-level semantics from fine image-level visual-semantic information. In addition, semantic latent channels are introduced as computational representation channels generated from observed visual EEG signals, expanding the channel-level semantic representation space for structured semantic abstraction and cross-modal alignment. Extensive experiments on the THINGS-EEG benchmark demonstrate that the proposed method achieves superior performance under subject-dependent zero-shot evaluation and improved exact retrieval under subject-independent zero-shot evaluation. Additional analyses, including layer-wise retrieval, temporal accumulation, expanded multi-image retrieval, and ablation studies, further support the effectiveness of staged decomposition and structured semantic modeling. These results suggest that explicitly modeling staged perceptual, semantic, and integrative representations provides an effective neuroscience-inspired framework for EEG-based visual decoding.

Problem

• EEG visual decoding
• staged representation
• hierarchical visual processing
• cross-modal alignment
• semantic modeling

Innovation

• staged representation learning
• disentangled semantics
• EEG visual decoding
• semantic latent channels
• neuroscience-inspired framework