Neural Visual Decoding via Cognitive guided Adaptive Blurring and Information Constrained Alignment

2026-05-14

AI Summary

This work addresses the challenges of mismatched information granularity and low signal-to-noise ratio in EEG-based visual decoding by proposing a Cognition-guided Adaptive Image Alignment (CAIA) framework. CAIA integrates neural oscillation priors with an information bottleneck mechanism to simulate visual selective attention through cognition-driven adaptive blurring. It further enhances cross-modal alignment via a distribution-aware boundary calibration loss. Evaluated on zero-shot brain-to-image retrieval tasks, CAIA significantly outperforms existing methods under both subject-dependent and subject-independent settings, while also improving model robustness and interpretability.

Abstract

EEG-based visual decoding aims to establish a mapping between neural signals and visual semantics. However, it remains constrained by the dual challenges of severe information granularity mismatch and the low signal-to-noise ratio (SNR) of EEG signals. Existing approaches typically treat static visual features, ignoring the dynamic selectivity of human vision and the frequency specificity of neural oscillations. To bridge this gap, we propose CAIA, a Cognitive-guided Adaptive blurring with Information-Constrained Alignment framework for Neural-Visual decoding. On the visual side, it simulates selective attention to adaptively reduce redundancy. Meanwhile, on the EEG side, it leverages neural oscillation priors and the information bottleneck mechanism to enhance SNR. Specifically, we devise a cognitive-dynamics-based adaptive blurring mechanism that dynamically integrates center-biased and saliency-guided visual cues via cross-modal attention. Furthermore, we introduce a distribution-aware boundary calibration loss to robustly rectify alignment bias caused by outlier samples. Moreover, a cognitively-guided information-screening method is proposed to select task-relevant EEG oscillations. Extensive experiments demonstrate that CAIA improves both subject-dependent and subject-independent average Top-1 and Top-5 accuracy in zero-shot brain-to-image retrieval, significantly outperforming prior methods. Our work validates that optimizing visual information density to match neural granularity offers a more interpretable and robust pathway for neural decoding.

Problem

• EEG-based visual decoding
• information granularity mismatch
• low signal-to-noise ratio
• dynamic visual selectivity
• neural oscillations

Innovation

• adaptive blurring
• information bottleneck
• neural oscillations
• cross-modal attention
• zero-shot brain-to-image retrieval