ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding

TL;DR

ViEEG introduces a hierarchical neural encoding framework for EEG-based visual decoding, significantly improving zero-shot object recognition by modeling the brain's visual processing hierarchy and aligning EEG features with visual concepts.

Contribution

The paper proposes ViEEG, a novel hierarchical EEG encoding model that captures the brain's visual hierarchy and enables zero-shot recognition, outperforming previous flat encoding methods.

Findings

Outperforms previous methods on THINGS-EEG dataset

Generalizes well across neural modalities like MEG

Advances EEG brain decoding with hierarchical modeling

Abstract

Understanding and decoding brain activity into visual representations is a fundamental challenge at the intersection of neuroscience and artificial intelligence. While EEG visual decoding has shown promise due to its non-invasive, and low-cost nature, existing methods suffer from Hierarchical Neural Encoding Neglect (HNEN)-a critical limitation where flat neural representations fail to model the brain's hierarchical visual processing hierarchy. Inspired by the hierarchical organization of visual cortex, we propose ViEEG, a neuro-We further adopt hierarchical contrastive learning for EEG-CLIP representation alignment, enabling zero-shot object recognition. Extensive experiments on the THINGS-EEG dataset demonstrate that ViEEG significantly outperforms previous methods by a large margin in both subject-dependent and subject-independent settings. Results on the THINGS-MEG dataset further confirm ViEEG's generalization to different neural modalities. Our framework not only advances the performance frontier but also sets a new paradigm for EEG brain decoding. inspired framework that addresses HNEN. ViEEG decomposes each visual stimulus into three biologically aligned components-contour, foreground object, and contextual scene-serving as anchors for a three-stream EEG encoder. These EEG features are progressively integrated via cross-attention routing, simulating cortical information flow from low-level to high-level vision.