mlsanityData to 14 Oct 2026

DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels

arXiv 2503.18536 ↗First posted 24 Mar 2025cs.CVcited by 2

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Medical Visual Question Answering (Med-VQA) systems benefit the interpretation of medical images containing critical clinical information. However, the challenge of noisy labels and limited high-quality datasets remains underexplored. To address this, we establish the first benchmark for noisy labels in Med-VQA by simulating human mislabeling with semantically designed noise types. More importantly, we introduce the DiN framework, which leverages a diffusion model to handle noisy labels in Med-VQA. Unlike the dominant classification-based VQA approaches that directly predict answers, our Answer Diffuser (AD) module employs a coarse-to-fine process, refining answer candidates with a diffusion model for improved accuracy. The Answer Condition Generator (ACG) further enhances this process by generating task-specific conditional information via integrating answer embeddings with fused image-question features. To address label noise, our Noisy Label Refinement(NLR) module introduces a robust loss function and dynamic answer adjustment to further boost the performance of the AD module.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 34 of its 51 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

34 of 51 references.

References · 34

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2017On Calibration of Modern Neural Networkscited by 4,960
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  10. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  11. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  12. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
22 more
  1. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  2. 2017Deep Learning for Medical Image Analysiscited by 401
  3. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  4. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
  5. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  6. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  7. 2022CARD: Classification and Regression Diffusion Modelscited by 103
  8. 2021Medical Visual Question Answering: A Surveycited by 93
  9. 2023Diffusion Recommender Modelcited by 88
  10. 2021Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?cited by 85
  11. 2019Overcoming Data Limitation in Medical Visual Question Answeringcited by 71
  12. 2021MMBERT: Multimodal BERT Pretraining for Improved Medical VQAcited by 68
  13. 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
  14. 2022Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformercited by 59
  15. 2021Multiple Meta-model Quantifying for Medical Visual Question Answeringcited by 54
  16. 2023Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answeringcited by 51
  17. 2020Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answeringcited by 32
  18. 2023Q2ATransformer: Improving Medical VQA via an Answer Querying Decodercited by 31
  19. 2023Alternate Diverse Teaching for Semi-supervised Medical Image Segmentationcited by 22
  20. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
  21. 2024Hallucination Benchmark in Medical Visual Question Answeringcited by 18
  22. 2022From Pixels to Objects: Cubic Visual Attention for Visual Question Answeringcited by 7

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopycited by 11
  2. 2025Multimodal LLM With Hierarchical Mixture-of-Experts for VQA on 3D Brain MRIcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2023Visual Question Answering in the Medical Domain
  2. 2024MISS: A Generative Pretraining and Finetuning Approach for Med-VQA
  3. 2026Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQA
  4. 2026MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering
  5. 2026MedFG-VQA: Low-Frequency Memory and Graph Attention for Lightweight Medical VQA
  6. 2025Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
  7. 2024MedThink: Explaining Medical Visual Question Answering via Multimodal Decision-Making Rationale
  8. 2025Knowing or Guessing? Robust Medical Visual Question Answering via Joint Consistency and Contrastive Learning