paper-with-me

홈 › Papers

SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering

2021-02-18 · Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, Xiao-Ming Wu

Medical visual question answering (Med-VQA) has tremendous potential in healthcare. However, the development of this technology is hindered by the lacking of publicly-available and high-quality labeled datasets for training and evaluation. In this paper, we present a large bilingual dataset, SLAKE, with comprehensive semantic labels annotated by experienced physicians and a new structural medical knowledge base for Med-VQA. Besides, SLAKE includes richer modalities and covers more human body parts than the currently available dataset. We show that SLAKE can be used to facilitate the development and evaluation of Med-VQA systems. The dataset can be downloaded from http://www.med-vqa.com/slake.

📄 PDF Abstract BibTeX arXiv:2102.09542

Code (2)

pengfeiliheu/m2i2 pytorch
pengfeiliheu/mumc pytorch

Tasks

Medical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets

2025-04-16 · Yongpei Ma, Pengyu Wang, Adam Dunn, Usman Naseem 외

Medical Visual Question Answering (MVQA) systems can interpret medical images in response to natural language queries. However, linguistic variability in question phrasing often undermines the consistency of these system…

DiversityMedical Visual Question AnsweringNatural Language QueriesQuestion Answering+3

KG-CMI: Knowledge graph enhanced cross-Mamba interaction for medical visual question answering

2026-04-01 · Xianyao Zheng, Hong Yu, Hui Cui, Changming Sun 외 arxiv

Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent methods fail to fully leverage domain-specific medical knowledge, making it difficult to accu…

Knowledge Graph EmbeddingVisual Question AnsweringMulti-Task Learning

A Causal Approach to Mitigate Modality Preference Bias in Medical Visual Question Answering

2025-05-22 · Shuchang Ye, Usman Naseem, Mingyuan Meng, Dagan Feng 외

Medical Visual Question Answering (MedVQA) is crucial for enhancing the efficiency of clinical diagnosis by providing accurate and timely responses to clinicians' inquiries regarding medical images. Existing MedVQA model…

counterfactualMedical Visual Question AnsweringQuestion AnsweringVisual Question Answering+1

Semantically Enhanced Models for Commonsense Knowledge Acquisition

2018-09-12 · Ikhlas Alhussien, Erik Cambria, Zhang NengSheng

Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this pap…

Graph EmbeddingKnowledge Base CompletionKnowledge Graph Embedding

MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale

2024-04-18 · Xiaotang Gai, Chenyi Zhou, Jiaxiang Liu, Yang Feng 외

Medical Visual Question Answering (MedVQA), which offers language responses to image-based medical inquiries, represents a challenging task and significant advancement in healthcare. It assists medical experts to swiftly…

Decision MakingMedical Visual Question AnsweringQuestion AnsweringVisual Question Answering+1