MedKCO：通过知识驱动的认知编排进行医学视觉语言预训练
MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration
把课程学习引入医学视觉语言预训练的数据排序与对比目标调度，提供了一种按诊断敏感性和类内代表性组织预训练数据、并用自步非对称对比损失缓解类间相似性干扰的可复用训练策略。
原文依据 we design a two level curriculum by incorporating diagnostic sensitivity and intra-class sample representativeness for the ordering of the pretraining data
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学视觉语言预训练（VLP）模型近期因其对多种下游任务的泛化能力而受到研究。然而，当前的医学VLP方法通常迫使模型同时学习简单与复杂概念。这种反认知的过程导致特征表示次优，在分布偏移下尤为明显。为解决这一局限，我们提出面向医学VLP的知识驱动认知编排（MedKCO），它同时涉及预训练数据的排序与视觉语言对比的学习目标。具体而言，我们设计了一个两级课程，将诊断敏感性与类内样本代表性纳入预训练数据的排序。此外，考虑到医学图像的类间相似性，我们引入自步非对称对比损失，以动态调整预训练目标的参与程度。我们在三个医学影像场景的多个视觉语言下游任务上评估所提出的预训练方法，并与若干课程学习方法进行比较。大量实验表明，我们的方法显著超越所有基线。https://github.com/Mr-Talon/MedKCO。
英文原文摘要 1242 字符
Medical vision-language pretraining (VLP) models have recently been investigated for their generalization to diverse downstream tasks. However, current medical VLP methods typically force the model to learn simple and complex concepts simultaneously. This anti-cognitive process leads to suboptimal feature representations, especially under distribution shift. To address this limitation, we propose a Knowledge-driven Cognitive Orchestration for Medical VLP (MedKCO) that involves both the ordering of the pretraining data and the learning objective of vision-language contrast. Specifically, we design a two level curriculum by incorporating diagnostic sensitivity and intra-class sample representativeness for the ordering of the pretraining data. Moreover, considering the inter-class similarity of medical images, we introduce a self-paced asymmetric contrastive loss to dynamically adjust the participation of the pretraining objective. We evaluate the proposed pretraining method on three medical imaging scenarios in multiple vision-language downstream tasks, and compare it with several curriculum learning methods. Extensive experiments show that our method significantly surpasses all baselines. https://github.com/Mr-Talon/MedKCO.