放射学中视觉-语言预训练的现实检验：我们使用文本取得进展了吗？
A Reality Check of Vision-Language Pre-training in Radiology: Have We Progressed Using Text?
AI总结：
本文重新审视放射学中视觉-语言预训练的实际效果，通过广泛比较证明使用细粒度标签的单模态预训练更具竞争力且更易整合异构数据，并质疑现有视觉-语言模型的开放词汇泛化潜力，同时探索融合细粒度标签与噪声文本监督的新方法。
摘要：
视觉-语言预训练近来因其能够利用大规模数据源学习丰富特征表示而受到欢迎。这一范式迅速进入了医学图像分析领域。特别是，近期有大量文献致力于开发面向放射学的视觉-语言模型。然而，可用的带有图像-文本监督的医学数据集十分稀缺，且医学概念是细粒度的，涉及现有视觉-语言模型难以编码的专家知识。在本文中，我们提议从文献中谨慎地退后一步，转而重新审视使用细粒度标签的有监督单模态预训练。我们进行了广泛的比较，证明单模态预训练具有高度竞争力，并且更适合整合异构数据源。我们的结果还对近期视觉-语言模型在开放词汇泛化方面的潜力提出了质疑，这些模型此前是在乐观的实验设置下进行评估的。最后，我们研究了新的替代方案，以更好地整合细粒度标签和带噪声的文本监督。
英文摘要：
Vision-language pre-training has recently gained popularity as it allows learning rich feature representations using large-scale data sources. This paradigm has quickly made its way into the medical image analysis community. In particular, there is an impressive amount of recent literature developing vision-language models for radiology. However, the available medical datasets with image-text supervision are scarce, and medical concepts are fine-grained, involving expert knowledge that existing vision-language models struggle to encode. In this paper, we propose to take a prudent step back from the literature and revisit supervised, unimodal pre-training, using fine-grained labels instead. We conduct an extensive comparison demonstrating that unimodal pre-training is highly competitive and better suited to integrating heterogeneous data sources. Our results also question the potential of recent vision-language models for open-vocabulary generalization, which have been evaluated using optimistic experimental settings. Finally, we study novel alternatives to better integrate fine-grained labels and noisy text supervision.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
