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.
Abstract (translated)
训练大规模数据 foundation models 获得了 cv 和 nlp 领域的近期增长,而生物医学领域的开发由于数据缺乏而落后很远。为了解决这个问题,我们建造并发布了 PMC-OA,这是一个从PubMed Central的开放获取部分收集的1600万图像标题对的生物医学数据集,比之前扩大了8倍。PMC-OA涵盖了多种模式或疾病,其中大多数图像标题样本对齐了更精细的水平,即小数点后面的小数部分和标题。在 PMC-OA 上进行CLIP风格模型的前训练时,我们开发了名为 PMC-CLIP 的模型,并在各种后续任务中取得了最先进的结果,包括ROCO图像文本检索、MedMNIST图像分类和医学问答QA(即图像文本检索准确率提高8.1%,图像分类准确率提高3.9%)。
URL
https://arxiv.org/abs/2303.07240