Metraipolis › archive › dc_3cfbbb577e02

MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA — arXiv:2608.26848

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26848
License (as archived): CC0-1.0
Archived: 2026-10-17T14:30:12.202Z
SHA-256 of the archived text: f520f7cedb098004bbe7c6b3b96b8547de9db7852cd77d5d6d0e5f0f49a6feee
Stable URL of this page: https://metraipolis.com/documento/dc_3cfbbb577e02

How to cite

MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA — arXiv:2608.26848 — arXiv (en), https://arxiv.org/abs/2608.26848 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cfbbb577e02 (Metraipolis archive dc_3cfbbb577e02, sha256 f520f7cedb098004bbe7c6b3b96b8547de9db7852cd77d5d6d0e5f0f49a6feee)

BibTeX

@misc{dc3cfbbb577e02,
  title = {MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA — arXiv:2608.26848},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26848},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cfbbb577e02; sha256 f520f7cedb098004bbe7c6b3b96b8547de9db7852cd77d5d6d0e5f0f49a6feee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26848. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26848 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.668Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).