Search papers, labs, and topics across Lattice.
This paper introduces MedFG-VQA, a lightweight framework for Medical Visual Question Answering (Med-VQA) that addresses the challenges of limited annotated data and high computational demands. By utilizing Frequency-Memory Fusion (FMF) to enhance low-frequency features and Graph-Aware Cross-Attention (GACA) for visual-textual alignment, the model achieves competitive performance with significantly lower computational costs. The creation of the SynMed-VQA dataset, comprising over 2 million synthetic question-answer pairs, further supports the framework's efficacy across various biomedical benchmarks.
MedFG-VQA achieves superior performance in medical VQA tasks while being lightweight enough for practical clinical use, thanks to innovative memory and graph attention techniques.
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.
