论文标题
测试时间无监督的域适应
Test-time Unsupervised Domain Adaptation
论文作者
论文摘要
接受公开可用的医学成像数据集培训的卷积神经网络（源域）很少概括为不同的扫描仪或采集协议（目标域）。这激发了域适应的主动领域。尽管某些问题的方法需要来自目标域的标记数据，但其他方法则采用无监督的方法来适应（UDA）。评估UDA方法包括测量模型在目标域中概括地看不见数据的能力。在这项工作中，我们认为这不像直接适应测试集一样有用。因此，我们提出了一个评估框架，在该框架中我们分别对每个主题进行测试时间UDA。我们表明，从目标域中适应特定目标主题的模型优于域适应方法，该方法看到了目标域的更多数据，但没有该特定目标主题。该结果支持以下论点：即使仅使用单个目标域受试者，也应在测试时间使用无监督的域适应性
Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation. While some approaches to the problem require labeled data from the target domain, others adopt an unsupervised approach to domain adaptation (UDA). Evaluating UDA methods consists of measuring the model's ability to generalise to unseen data in the target domain. In this work, we argue that this is not as useful as adapting to the test set directly. We therefore propose an evaluation framework where we perform test-time UDA on each subject separately. We show that models adapted to a specific target subject from the target domain outperform a domain adaptation method which has seen more data of the target domain but not this specific target subject. This result supports the thesis that unsupervised domain adaptation should be used at test-time, even if only using a single target-domain subject
