Recent advances in image-text pretraining have significantly enhanced visual understanding by aligning visual and textual representations. Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning. However, its focus on single-label, single-granularity alignment limits its effectiveness in complex domains such as medical imaging, where images often correspond to multiple high-level labels (e.g., disease categories) across different annotation granularities (e.g., diagnostic description, clinical explanation). To address this, we propose Multi-Granular Language Learning (MGLL), a contrastive learning framework designed to improve both multi-label and cross-granularity alignment. MGLL leverages structured multi-label supervision, integrates textual descriptions across granularities, and introduces soft-label supervision with point-wise constraints to enhance alignment. MGLL employs smooth Kullback-Leibler (KL) divergence to ensure cross-granularity consistency while maintaining computational efficiency as a plug-and-play module for vision-language models. Pretrained on our constructed large-scale multi-granular datasets and evaluated across multiple datasets, MGLL outperforms other state-of-the-art methods in downstream tasks. The code is available at https://github.com/HUANGLIZI/MGLL.

翻译：近年来，图像-文本预训练通过对齐视觉与文本表示，显著提升了视觉理解能力。对比语言-图像预训练（CLIP）在多模态学习中发挥了关键作用。然而，其专注于单标签、单粒度的对齐方式限制了其在复杂领域（如医学影像）中的有效性，因为医学图像通常对应多个高层级标签（例如疾病类别），且标注粒度各异（如诊断描述、临床解释）。为此，我们提出多粒度语言学习（MGLL），这是一种旨在改进多标签与跨粒度对齐的对比学习框架。MGLL利用结构化的多标签监督，整合不同粒度的文本描述，并引入带逐点约束的软标签监督以增强对齐效果。MGLL采用平滑的Kullback-Leibler（KL）散度来确保跨粒度一致性，同时作为视觉-语言模型的即插即用模块保持计算效率。在我们构建的大规模多粒度数据集上进行预训练，并在多个数据集上评估，MGLL在下游任务中优于其他最先进方法。代码发布于 https://github.com/HUANGLIZI/MGLL。