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

TL;DR

This paper introduces CAIA, a novel framework that enhances EEG-based visual decoding by simulating attention, leveraging neural oscillation priors, and aligning visual and neural information for improved accuracy.

Contribution

It proposes a comprehensive cognitive-guided adaptive blurring and information alignment method that addresses neural signal noise and information mismatch in visual decoding.

Findings

CAIA significantly improves zero-shot brain-to-image retrieval accuracy.

The method outperforms prior approaches in both subject-dependent and subject-independent settings.

Enhanced interpretability and robustness in neural decoding are achieved through optimized visual information density.

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.