English

PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents

Computer Vision and Pattern Recognition 2023-03-14 v1 Computation and Language Machine Learning Multimedia

Abstract

Foundation models trained on large-scale dataset gain a recent surge in CV and NLP. In contrast, development in biomedical domain lags far behind due to data scarcity. To address this issue, we build and release PMC-OA, a biomedical dataset with 1.6M image-caption pairs collected from PubMedCentral's OpenAccess subset, which is 8 times larger than before. PMC-OA covers diverse modalities or diseases, with majority of the image-caption samples aligned at finer-grained level, i.e., subfigure and subcaption. While pretraining a CLIP-style model on PMC-OA, our model named PMC-CLIP achieves state-of-the-art results on various downstream tasks, including image-text retrieval on ROCO, MedMNIST image classification, Medical VQA, i.e. +8.1% R@10 on image-text retrieval, +3.9% accuracy on image classification.

Keywords

Cite

@article{arxiv.2303.07240,
  title  = {PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents},
  author = {Weixiong Lin and Ziheng Zhao and Xiaoman Zhang and Chaoyi Wu and Ya Zhang and Yanfeng Wang and Weidi Xie},
  journal= {arXiv preprint arXiv:2303.07240},
  year   = {2023}
}

Comments

10 pages, 3 figures

R2 v1 2026-06-28T09:14:29.373Z