Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training

TL;DR

Uni-Mlip is a novel self-supervised framework that enhances medical vision-language pre-training by integrating multiple self-supervision techniques, leading to superior performance in various downstream medical tasks.

Contribution

It introduces a unified self-supervision approach tailored for medical data, combining cross-modality, uni-modality, and fused-modality methods at data and feature levels.

Findings

Outperforms state-of-the-art methods in image-text retrieval

Achieves higher accuracy in medical image classification

Improves results in visual question answering tasks

Abstract

Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due to privacy, sensitivity, and annotation complexity. To mitigate data scarcity while boosting model performance, we introduce \textbf{Uni-Mlip}, a unified self-supervision framework specifically designed to enhance medical vision-language pre-training. Uni-Mlip seamlessly integrates cross-modality, uni-modality, and fused-modality self-supervision techniques at the data-level and the feature-level. Additionally, Uni-Mlip tailors uni-modal image self-supervision to accommodate the unique characteristics of medical images. Our experiments across datasets of varying scales demonstrate that Uni-Mlip significantly surpasses current state-of-the-art methods in three key downstream tasks: image-text retrieval, image classification, and visual question answering (VQA).