The current state-of-the art techniques for image segmentation are often based on U-Net architectures, a U-shaped encoder-decoder networks with skip connections. Despite the powerful performance, the architecture often does not perform well when used on data which has different characteristics than the data it was trained on. Many techniques for improving performance in the presence of domain shift have been developed, however typically only have loose connections to the theory of domain adaption. In this work, we propose an unsupervised domain adaptation framework for U-Nets with theoretical guarantees based on the Margin Disparity Discrepancy [1] called the MDD-UNet. We evaluate the proposed technique on the task of hippocampus segmentation, and find that the MDD-UNet is able to learn features which are domain-invariant with no knowledge about the labels in the target domain. The MDD-UNet improves performance over the standard U-Net on 11 out of 12 combinations of datasets. This work serves as a proof of concept by demonstrating an improvement on the U-Net in it's standard form without modern enhancements, which opens up a new avenue of studying domain adaptation for models with very large hypothesis spaces from both methodological and practical perspectives. Code is available at https://github.com/asbjrnmunk/mdd-unet.

翻译：当前最先进的图像分割技术多基于U-Net架构，这是一种带有跳跃连接的U形编码器-解码器网络。尽管性能强大，但当处理与训练数据特征不同的数据时，该架构通常表现不佳。目前已发展出多种提升域偏移下性能的技术，但大多与域适应理论的关联较为松散。本研究提出一种基于边际差异不一致性[1]的U-Net无监督域适应框架，称为MDD-UNet，该方法具有理论保证。我们采用该技术在海马体分割任务上进行评估，发现MDD-UNet能够在未知目标域标签的情况下学习域不变特征。在12个数据集组合中，MDD-UNet在11个组合上的性能优于标准U-Net。本研究作为概念验证，展示了无需现代增强的原始U-Net性能的提升，为从方法学和实践角度研究具有极大假设空间模型的域适应开辟了新途径。代码已开源至https://github.com/asbjrnmunk/mdd-unet。