视觉语言预训练粒度是否重要？跨胸部X射线解读任务的视觉语言目标受控评估
Does Vision-Language Pretraining Granularity Matter? A Controlled Evaluation of Vision-Language Objectives Across Chest X-Ray Interpretation Tasks
浏览论文内容
中文总结 AI 辅助
本研究通过控制预训练目标，评估九种视觉语言目标在五个胸部X射线任务上的表现，发现预训练粒度与任务粒度对齐，且无单一目标普遍最优，目标类型、粒度和任务共同决定下游性能。
中文摘要 AI 辅助
视觉语言预训练目标在监督的空间粒度上有所不同，然而这种分布对胸部X射线解读的影响仍未得到充分探索。我们提出了一项受控研究，以隔离预训练目标：在保持编码器和预训练数据固定的情况下，我们训练了九个目标，涵盖全局和局部对比学习、字幕生成及其组合，并在五个空间粒度递增的胸部X射线任务上进行了评估。我们发现：(i) 在极端情况下，预训练粒度与任务粒度对齐，局部目标在异常检测上领先，而全局目标在分类上领先；(ii) 局部目标在全局级别的生成和问答任务上出人意料地具有竞争力；(iii) 字幕生成和对比学习的优点在不同粒度级别上发生逆转；(iv) 在组合中，混合字幕生成和对比监督在分类和分布内生成上最强，而配对两个字幕生成目标在零样本报告生成上泛化最佳。这些结果表明，没有单一目标普遍最优，目标类型、粒度和任务的交互作用决定了下游性能。
英文摘要
Vision-language pretraining objectives differ in the spatial granularity of their supervision, yet the implications of this distribution for chest X-ray interpretation remain underexplored. We present a controlled study that isolates the pretraining objective: holding the encoder and pretraining data fixed, we train nine objectives spanning global and local contrastive learning, captioning, and their combinations, and evaluate across five chest X-ray tasks of increasing spatial granularity. We find that (i) pretraining granularity aligns with task granularity at the extremes, with local objectives leading on abnormality detection and global objectives on classification; (ii) local objectives are surprisingly competitive on global-level generation and question answering tasks; (iii) the merits of captioning and contrastive learning reverse across granularity levels; and (iv) among combinations, mixing captioning and contrastive supervision is strongest on classification and in distribution generation, while pairing two captioning objectives generalizes best on zero-shot report generation. These results show that no single objective is universally optimal, and that the interaction of objective type, granularity, and task governs downstream performance.
