Unveiling Deep Semantic Uncertainty Perception for Language-Anchored Multi-modal Vision-Brain Alignment

TL;DR

This paper introduces Bratrix, an innovative end-to-end framework that aligns visual stimuli, neural signals, and language representations into a shared space, improving interpretability and robustness in neural-visual-linguistic tasks.

Contribution

Bratrix is the first framework to decouple visual and linguistic semantics for multimodal brain alignment, incorporating uncertainty modeling and a two-stage training strategy for enhanced performance.

Findings

Outperforms state-of-the-art in EEG, MEG, and fMRI tasks.

Surpasses 14.3% improvement in EEG retrieval accuracy.

Enhances neural-visual-linguistic alignment and interpretability.

Abstract

Unveiling visual semantics from neural signals such as EEG, MEG, and fMRI remains a fundamental challenge due to subject variability and the entangled nature of visual features. Existing approaches primarily align neural activity directly with visual embeddings, but visual-only representations often fail to capture latent semantic dimensions, limiting interpretability and deep robustness. To address these limitations, we propose Bratrix, the first end-to-end framework to achieve multimodal Language-Anchored Vision-Brain alignment. Bratrix decouples visual stimuli into hierarchical visual and linguistic semantic components, and projects both visual and brain representations into a shared latent space, enabling the formation of aligned visual-language and brain-language embeddings. To emulate human-like perceptual reliability and handle noisy neural signals, Bratrix incorporates a novel uncertainty perception module that applies uncertainty-aware weighting during alignment. By leveraging learnable language-anchored semantic matrices to enhance cross-modal correlations and employing a two-stage training strategy of single-modality pretraining followed by multimodal fine-tuning, Bratrix-M improves alignment precision. Extensive experiments on EEG, MEG, and fMRI benchmarks demonstrate that Bratrix improves retrieval, reconstruction, and captioning performance compared to state-of-the-art methods, specifically surpassing 14.3% in 200-way EEG retrieval task. Code and model are available.