数字病理图像的适应性域泛化
Adaptive Domain Generalization for Digital Pathology Images
AI总结：
针对数字病理图像中不可见域偏移，提出反应式域泛化技术，通过测试时训练自适应调整模型参数，无需训练时预测偏移。
摘要：
在基于人工智能的组织病理学中，域偏移是常见且被充分研究的现象。然而，本研究关注的是染色和扫描仪的变化，这些并未展示全貌——偏移可能是其他偏移的组合，或是“不可见”的偏移，这些偏移虽不明显但仍会损害机器学习模型的性能。此外，模型能够泛化到这些偏移而不需要昂贵或稀缺的标注，这一点至关重要，尤其是在组织病理学领域以及希望大规模部署模型的情况下。因此，需要“反应式”域泛化技术：即在测试时适应域偏移，而非在训练时要求预测偏移或提供偏移示例。我们进行了文献综述，并介绍了能够对域偏移做出反应而非预先要求预测这些偏移的技术。我们研究了测试时训练，这是一种域泛化技术，通过在测试时优化一个次要的自监督任务来调整模型参数。
英文摘要：
In AI-based histopathology, domain shifts are common and well-studied. However, this research focuses on stain and scanner variations, which do not show the full picture -- shifts may be combinations of other shifts, or "invisible" shifts that are not obvious but still damage performance of machine learning models. Furthermore, it is important for models to generalize to these shifts without expensive or scarce annotations, especially in the histopathology space and if wanting to deploy models on a larger scale. Thus, there is a need for "reactive" domain generalization techniques: ones that adapt to domain shifts at test-time rather than requiring predictions of or examples of the shifts at training time. We conduct a literature review and introduce techniques that react to domain shifts rather than requiring a prediction of them in advance. We investigate test time training, a technique for domain generalization that adapts model parameters at test-time through optimization of a secondary self-supervised task.
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。
