MedCLIP: Contrastive Learning from Unpaired Medical Images and Text

Zifeng Wang, Zhenbang Wu, Dinesh Agarwal, Jimeng Sun

Research output: Contribution to conferencePaperpeer-review


Existing vision-text contrastive learning like CLIP (Radford et al., 2021) aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical image-text datasets are orders of magnitude below the general images and captions from the internet. Moreover, previous methods encounter many false negatives, i.e., images and reports from separate patients probably carry the same semantics but are wrongly treated as negatives. In this paper, we decouple images and texts for multimodal contrastive learning thus scaling the usable training data in a combinatorial magnitude with low cost. We also propose to replace the InfoNCE loss with semantic matching loss based on medical knowledge to eliminate false negatives in contrastive learning. We prove that MedCLIP is a simple yet effective framework: it outperforms state-of-the-art methods on zero-shot prediction, supervised classification, and image-text retrieval. Surprisingly, we observe that with only 20K pre-training data, MedCLIP wins over the state-of-the-art method (using ≈ 200K data).

Original languageEnglish (US)
Number of pages12
StatePublished - 2022
Externally publishedYes
Event2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022 - Abu Dhabi, United Arab Emirates
Duration: Dec 7 2022Dec 11 2022


Conference2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems


Dive into the research topics of 'MedCLIP: Contrastive Learning from Unpaired Medical Images and Text'. Together they form a unique fingerprint.

Cite this