面向视觉解耦的语言先验：迈向对称的视觉-大脑对齐
Linguistic Priors for Visual Decoupling: Towards Symmetric Vision-Brain Alignment
用面向物体的文本描述作为语义先验，把自然图像中的前景物体与背景显式解耦，再与含噪脑信号做语义对称对齐；这套「语言先验引导的视觉解耦」思路可迁移到图像-文本-神经信号三模态对齐、以及需要抑制背景干扰的跨模态检索任务。
原文依据 introduces object-oriented textual descriptions as semantic guidance to explicitly decouple foreground objects from complex backgrounds
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大脑视觉解码旨在从大脑活动中识别并重建感知到的视觉内容，为脑机接口与类脑智能的发展提供了广阔前景。然而，该任务面临信息不对称这一根本性挑战：自然图像包含由物体与背景构成的复杂视觉场景，而对应的脑信号反映的是对中心物体的聚焦注意，同时受到各类神经噪声的污染。以往直接将视觉表征与大脑表征对齐的方法往往忽视了这种固有的不对称性，导致解码性能欠佳。为解决这一问题，我们提出语言先验引导的视觉解耦方法，引入面向物体的文本描述作为语义引导，将前景物体从自然图像的复杂背景中显式解耦。该设计使模型能够自动聚焦于任务相关的视觉概念，同时有效滤除脑信号中的无关神经噪声，实现从不对称的视觉-大脑对齐向语义对称对齐的转变。在 THINGS-EEG 与 THINGS-MEG 数据集上的大量实验表明，我们的方法在零样本大脑到图像检索任务上取得了新的最优性能。源代码已发布于 https://github.com/TKQXX/BVSA。
英文原文摘要 1394 字符
Brain visual decoding aims to recognize and reconstruct perceptual visual content from brain activity, providing a promising potential for the development of brain-computer interfaces and brain-inspired intelligence. However, this task faces a fundamental challenge of information asymmetry: while natural images contain complex visual scenes with objects and backgrounds, the corresponding brain signals reflect focused attention on central objects while being contaminated by various neural noise. Previous methods that directly align visual and brain representations often overlook this inherent asymmetry, resulting in suboptimal decoding performance. To address this, we propose linguistic-prior-guided visual decoupling method, which introduces object-oriented textual descriptions as semantic guidance to explicitly decouple foreground objects from complex backgrounds in natural images. This design enables the model to automatically focus on task-relevant visual concepts while effectively filtering out irrelevant neural noise in brain signals, achieving a transition from asymmetric vision-brain alignment to semantic symmetric alignment. Extensive experiments on the THINGS-EEG and THINGS-MEG datasets demonstrate that our method achieves new state-of-the-art performance in the zero-shot brain-to-image retrieval task. The source code is available at https://github.com/TKQXX/BVSA.