VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering

IF 5.5 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Aiman Lameesa , Chaklam Silpasuwanchai , Md. Sakib Bin Alam
{"title":"VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering","authors":"Aiman Lameesa ,&nbsp;Chaklam Silpasuwanchai ,&nbsp;Md. Sakib Bin Alam","doi":"10.1016/j.neucom.2024.128730","DOIUrl":null,"url":null,"abstract":"<div><div>Image and question matching is essential in Medical Visual Question Answering (MVQA) in order to accurately assess the visual-semantic correspondence between an image and a question. However, the recent state-of-the-art methods focus solely on the contrastive learning between an entire image and a question. Though contrastive learning successfully model the global relationship between an image and a question, it is less effective to capture the fine-grained alignments conveyed between image regions and question words. In contrast, large-scale pre-training poses significant drawbacks, including extended training times, handling substantial data volumes, and necessitating high computational power. To address these challenges, we propose the Vision-Guided Cross-Attention based Late Fusion (VG-CALF) network, which integrates image and question features into a unified deep model without relying on pre-training for MVQA tasks. In our proposed approach, we use self-attention to effectively leverage intra-modal relationships within each modality and implement vision-guided cross-attention to emphasize the inter-modal relationships between image regions and question words. By simultaneously considering intra-modal and inter-modal relationships, our proposed method significantly improves the overall performance of MVQA without the need for pre-training on extensive image-question pairs. Experimental results on benchmark datasets, such as, SLAKE and VQA-RAD demonstrate that our proposed approach performs competitively with existing state-of-the-art methods.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"613 ","pages":"Article 128730"},"PeriodicalIF":5.5000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurocomputing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925231224015017","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Image and question matching is essential in Medical Visual Question Answering (MVQA) in order to accurately assess the visual-semantic correspondence between an image and a question. However, the recent state-of-the-art methods focus solely on the contrastive learning between an entire image and a question. Though contrastive learning successfully model the global relationship between an image and a question, it is less effective to capture the fine-grained alignments conveyed between image regions and question words. In contrast, large-scale pre-training poses significant drawbacks, including extended training times, handling substantial data volumes, and necessitating high computational power. To address these challenges, we propose the Vision-Guided Cross-Attention based Late Fusion (VG-CALF) network, which integrates image and question features into a unified deep model without relying on pre-training for MVQA tasks. In our proposed approach, we use self-attention to effectively leverage intra-modal relationships within each modality and implement vision-guided cross-attention to emphasize the inter-modal relationships between image regions and question words. By simultaneously considering intra-modal and inter-modal relationships, our proposed method significantly improves the overall performance of MVQA without the need for pre-training on extensive image-question pairs. Experimental results on benchmark datasets, such as, SLAKE and VQA-RAD demonstrate that our proposed approach performs competitively with existing state-of-the-art methods.
VG-CALF:医学视觉问题解答中用于放射学图像的视觉引导交叉注意和后期融合网络
为了准确评估图像和问题之间的视觉语义对应关系,图像和问题匹配在医学视觉问题解答(MVQA)中至关重要。然而,近期最先进的方法仅关注整个图像和问题之间的对比学习。虽然对比学习成功地模拟了图像和问题之间的全局关系,但在捕捉图像区域和问题词语之间的细粒度排列方面却不太有效。相比之下,大规模预训练具有明显的缺点,包括训练时间长、处理数据量大以及需要较高的计算能力。为了应对这些挑战,我们提出了基于视觉引导交叉注意力的后期融合(VG-CALF)网络,它将图像和问题特征整合到一个统一的深度模型中,而无需依赖 MVQA 任务的预训练。在我们提出的方法中,我们利用自我注意有效地利用每种模态内部的模态关系,并实施视觉引导交叉注意来强调图像区域和问题单词之间的模态关系。通过同时考虑模内和模间关系,我们提出的方法显著提高了 MVQA 的整体性能,而无需对大量图像-问题对进行预训练。在 SLAKE 和 VQA-RAD 等基准数据集上的实验结果表明,我们提出的方法与现有的最先进方法相比具有很强的竞争力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Neurocomputing
Neurocomputing 工程技术-计算机:人工智能
CiteScore
13.10
自引率
10.00%
发文量
1382
审稿时长
70 days
期刊介绍: Neurocomputing publishes articles describing recent fundamental contributions in the field of neurocomputing. Neurocomputing theory, practice and applications are the essential topics being covered.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信