Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering

• URL: http://arxiv.org/abs/2510.08791v1
• Date: Thu, 09 Oct 2025 20:14:49 GMT
• Title: Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
• Authors: Yuanhao Zou, Zhaozheng Yin,
• Abstract summary: Medical Visual Question Answering (Med-VQA) is a challenging task that requires a deep understanding of both medical images and textual questions.<n>Our framework outperforms the previous state-of-the-art on widely used Med-VQA datasets like RAD-VQA, SLAKE, PathVQA and VQA 2019.
• Score: 26.129050821950994
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Medical Visual Question Answering (Med-VQA) is a challenging task that requires a deep understanding of both medical images and textual questions. Although recent works leveraging Medical Vision-Language Pre-training (Med-VLP) have shown strong performance on the Med-VQA task, there is still no unified solution for modality alignment, and the issue of hard negatives remains under-explored. Additionally, commonly used knowledge fusion techniques for Med-VQA may introduce irrelevant information. In this work, we propose a framework to address these challenges through three key contributions: (1) a unified solution for heterogeneous modality alignments across multiple levels, modalities, views, and stages, leveraging methods like contrastive learning and optimal transport theory; (2) a hard negative mining method that employs soft labels for multi-modality alignments and enforces the hard negative pair discrimination; and (3) a Gated Cross-Attention Module for Med-VQA that integrates the answer vocabulary as prior knowledge and selects relevant information from it. Our framework outperforms the previous state-of-the-art on widely used Med-VQA datasets like RAD-VQA, SLAKE, PathVQA and VQA-2019.

Related papers

• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning [34.6490677122246]
  We show that current Medical Vision-Language Models (Med-VLMs) exhibit concerning fragility in Medical Visual Question Answering.<n>We propose Consistency and Contrastive Learning (CCL), which integrates knowledge-anchored consistency learning and bias-aware contrastive learning.<n>CCL achieves SOTA performance on three popular VQA benchmarks and notably improves answer consistency by 50% on the challenging RoMed test set.
  arXiv  Detail & Related papers  (2025-08-26T05:21:19Z)
• GEMeX-ThinkVG: Towards Thinking with Visual Grounding in Medical VQA via Reinforcement Learning [50.94508930739623]
  Medical visual question answering aims to support clinical decision-making by enabling models to answer natural language questions based on medical images.<n>Current methods still suffer from limited answer reliability and poor interpretability, impairing the ability of clinicians and patients to understand and trust model-generated answers.<n>This work first proposes a Thinking with Visual Grounding dataset wherein the answer generation is decomposed into intermediate reasoning steps.<n>We introduce a novel verifiable reward mechanism for reinforcement learning to guide post-training, improving the alignment between the model's reasoning process and its final answer.
  arXiv  Detail & Related papers  (2025-06-22T08:09:58Z)
• CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making [42.28216499263317]
  We introduce Med-Zero-17K, a curated dataset for pure RL-based training, encompassing over 30 medical image modalities and 24 clinical tasks.<n>We propose a novel large-scale RL framework for Med-VLMs, which integrates rewards to ensure fidelity between perception and reasoning, consistency in reasoning-to-answer, and rule-based accuracy for final responses.
  arXiv  Detail & Related papers  (2025-06-15T13:42:46Z)
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning [57.873833577058]
  We build a multimodal dataset enriched with extensive medical knowledge.<n>We then introduce our medical-specialized MLLM: Lingshu.<n>Lingshu undergoes multi-stage training to embed medical expertise and enhance its task-solving capabilities.
  arXiv  Detail & Related papers  (2025-06-08T08:47:30Z)
• Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion [4.821565717653691]
  Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis.<n>This study proposes a HiCA-VQA method, including two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders.<n> Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework better outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions.
  arXiv  Detail & Related papers  (2025-04-04T03:03:12Z)
• ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images [4.353855760968461]
  Cross-Modal Clinical Knowledge Distiller (ClinKD) designed to enhance image-text alignment and establish more effective medical knowledge transformation mechanisms.<n>ClinKD achieves state-of-the-art performance on several datasets which are challenging for Med-VQA task.
  arXiv  Detail & Related papers  (2025-02-09T15:08:10Z)
• Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering [7.669872220702526]
  We present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text. The proposed approach achieves state-of-the-art (SOTA) performance on three publicly available medical VQA datasets.
  arXiv  Detail & Related papers  (2023-07-11T15:00:11Z)
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering [56.25766322554655]
  Medical Visual Question Answering (MedVQA) presents a significant opportunity to enhance diagnostic accuracy and healthcare delivery. We propose a generative-based model for medical visual understanding by aligning visual information from a pre-trained vision encoder with a large language model. We train the proposed model on PMC-VQA and then fine-tune it on multiple public benchmarks, e.g., VQA-RAD, SLAKE, and Image-Clef 2019.
  arXiv  Detail & Related papers  (2023-05-17T17:50:16Z)
• Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training [55.56609500764344]
  We propose a unified framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework. We also introduce a Memory-Augmented Cross-Modal Fusion (MA-CMF) module to fully integrate visual information to assist report reconstruction.
  arXiv  Detail & Related papers  (2023-05-13T13:53:48Z)
• Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering [89.76059961309453]
  HeadQA dataset contains multiple-choice questions authorized for the public healthcare specialization exam. These questions are the most challenging for current QA systems. We present a Multi-step reasoning with Knowledge extraction framework (MurKe) We are striving to make full use of off-the-shelf pre-trained models.
  arXiv  Detail & Related papers  (2020-08-06T02:47:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.