让脑电解码更准：区分前景与背景，提升视觉理解精度
FSDBN: Foreground-Aware EEG-Visual Alignment via Dynamic Brain Networks
- 通过语义-显著性联合约束分离前景与背景
- 动态脑网络捕捉注意力变化，实现时变神经连接建模
- 零样本图像检索性能领先，适合脑机接口研究者
基于脑电的视觉解码为无创解析视觉语义提供了路径。然而，现有方法常忽略复杂场景中前景与背景的感知不对称性，导致背景干扰和语义错位。脑电信号还具有快速的时间动态性和非平稳的空间模式，难以捕捉与焦点视觉注意相关的时间变化脑连接。为此，我们提出FSDBN统一框架以实现鲁棒的脑电-视觉解码。FSDBN引入语义一致显著性对齐，在联合显著性和语义约束下分离语义相关的前景区域；进一步采用语义先验动态门控前景融合，自适应调节前景与背景特征的贡献。同时，将脑电信号建模为自适应时空脑网络，其功能连接动态重组以捕捉对显著前景的神经响应。在零样本脑到图像检索任务上，FSDBN达到69.0%的top-1准确率和92.2%的top-5准确率，优于此前最先进方法。代码已开源。
原文摘要 · Abstract (English)
EEG-based visual decoding provides a non-invasive pathway for interpreting visual semantics. However, existing methods often overlook the perceptual asymmetry between foreground and background in complex scenes, leading to background interference and semantic misalignment. EEG signals also exhibit rapid temporal dynamics and nonstationary spatial patterns, making it difficult to capture the time-varying brain connectivity associated with focal visual attention. To address these limitations, we propose FSDBN, a unified framework for robust EEG-visual decoding. FSDBN introduces Semantic-Consistent Saliency Alignment to separate semantically relevant foreground regions from background noise under joint saliency and semantic constraints. It further employs Semantic-Prior Dynamic Gating Foreground Fusion to adaptively regulate the contributions of foreground and background features. In parallel, EEG signals are modeled as adaptive spatiotemporal brain networks whose functional connectivity dynamically reorganizes to capture neural responses to salient foregrounds. Experiments on zero-shot brain-to-image retrieval demonstrate that FSDBN achieves 69.0 percent top-1 accuracy and 92.2 percent top-5 accuracy, outperforming previous state-of-the-art methods. Code is available at https://github.com/LiuYiheng1/FSDBN-EEG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。