Progressive Local Alignment for Medical Multimodal Pre-training
This work addresses the problem of precise medical image-text alignment for diagnosis, which is incremental as it builds on existing contrastive learning methods with a novel progressive strategy.
The paper tackles the challenge of local alignment between medical images and text for accurate diagnosis by proposing the Progressive Local Alignment Network (PLAN), which uses contrastive learning and progressive refinement to improve word-pixel relationships, resulting in state-of-the-art performance on phrase grounding, image-text retrieval, object detection, and zero-shot classification across multiple medical datasets.
Local alignment between medical images and text is essential for accurate diagnosis, though it remains challenging due to the absence of natural local pairings and the limitations of rigid region recognition methods. Traditional approaches rely on hard boundaries, which introduce uncertainty, whereas medical imaging demands flexible soft region recognition to handle irregular structures. To overcome these challenges, we propose the Progressive Local Alignment Network (PLAN), which designs a novel contrastive learning-based approach for local alignment to establish meaningful word-pixel relationships and introduces a progressive learning strategy to iteratively refine these relationships, enhancing alignment precision and robustness. By combining these techniques, PLAN effectively improves soft region recognition while suppressing noise interference. Extensive experiments on multiple medical datasets demonstrate that PLAN surpasses state-of-the-art methods in phrase grounding, image-text retrieval, object detection, and zero-shot classification, setting a new benchmark for medical image-text alignment.