Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training
This work addresses data scarcity challenges for medical AI applications, offering an incremental improvement by tailoring existing self-supervision methods to the medical domain.
The paper tackled the problem of data scarcity in medical vision-language pre-training by introducing Uni-Mlip, a unified self-supervision framework that integrates cross-modality, uni-modality, and fused-modality techniques, resulting in significant performance improvements over state-of-the-art methods in image-text retrieval, image classification, and visual question answering.
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).