MedFG-VQA：面向轻量级医学视觉问答的低频记忆与图注意力
MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
把 DCT 低频特征与可学习记忆库结合、再用图卷积聚合精炼交叉注意力输出的做法，可直接迁移到其他视觉-语言对齐任务（如 captioning、grounding）中做轻量化的多模态融合模块。
原文依据 employs graph-enhanced cross-attention for effective visual-textual alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学视觉问答（Med-VQA）在临床决策支持方面具有重要前景，但由于标注数据有限以及现有大型视觉-语言模型计算需求高，仍面临挑战。我们提出 MedFG-VQA，一个轻量级框架，利用记忆库增强基于 DCT 的低频特征，并采用图增强的交叉注意力实现有效的视觉-文本对齐。具体而言，我们的方法包含两个关键组件：频率-记忆融合（FMF），通过从基于 DCT 分解构建的可学习记忆库中检索来增强低频特征；以及图感知交叉注意力（GACA），通过交叉注意力对齐视觉-文本特征，并通过图卷积聚合对其进行精炼。为缓解数据稀缺问题，我们构建了 SynMed-VQA，这是一个大规模合成数据集，包含跨越 9 种成像模态和 10 个主要器官的超过 200 万个问答对，由 GPT-4o 生成。在 SynMed-VQA 及另外三个标准生物医学视觉问答基准上的大量实验表明，MedFG-VQA 在保持显著更低计算成本的同时，取得了与规模大得多的模型相当或更优的性能，凸显了其效率及临床部署潜力。
英文原文摘要 1300 字符
Medical Visual Question Answering (Med-VQA) holds significant promise for clinical decision support, yet faces challenges due to limited annotated data and the high computational demands of existing large vision-language models. We propose MedFG-VQA, a lightweight framework that leverages a memory bank to augment DCT-based low-frequency features and employs graph-enhanced cross-attention for effective visual-textual alignment. Specifically, our approach features two key components: Frequency-Memory Fusion (FMF), which enhances low-frequency features by retrieving from a learnable memory bank built on DCT decomposition, and Graph-Aware Cross-Attention (GACA), which aligns visual-textual features via cross-attention and refines them through graph-convolutional aggregation. To address data scarcity, we construct SynMed-VQA, a large-scale synthetic dataset comprising over 2 million question-answer pairs across 9 imaging modalities and 10 major organs, generated with GPT-4o. Extensive experiments on SynMed-VQA and three other standard biomedical VQA benchmarks demonstrate that MedFG-VQA achieves competitive or superior performance compared to much larger models while maintaining significantly lower computational costs, highlighting its efficiency and potential for clinical deployment.