In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set. However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. Hence, in this paper, we consider a new, more realistic, and more challenging problem setting where the pixel-level classifier has to be trained with labeled images and unlabeled open-world images -- we name it open-set domain adaptation segmentation (OSDAS). In OSDAS, the trained classifier is expected to identify unknown-class pixels and classify known-class pixels well. To solve OSDAS, we first investigate which distribution that unknown-class pixels obey. Then, motivated by the goodness-of-fit test, we use statistical measurements to show how a pixel fits the distribution of an unknown class and select highly-fitted pixels to form the unknown region in each test image. Eventually, we propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning the distributions of known classes in labeled and unlabeled open-world images. The effectiveness of KRADA has been verified on two synthetic tasks and one COVID-19 segmentation task.

翻译：在语义分割中，我们旨在训练一个像素级分类器，为图像中的所有像素分配类别标签，其中带标签的训练图像与未标签的测试图像来自相同分布且共享相同标签集。然而，在开放世界中，未标签的测试图像可能包含未知类别，并且与带标签图像的分布不同。因此，本文考虑了一种新的、更现实且更具挑战性的问题设定：像素级分类器必须使用带标签图像和未标签的开放世界图像进行训练——我们将其命名为开放集域自适应分割（OSDAS）。在OSDAS中，训练好的分类器需能准确识别未知类像素并良好分类已知类像素。为解决OSDAS，我们首先探究未知类像素服从何种分布；接着，受拟合优度检验启发，利用统计度量评估像素对未知类分布的拟合程度，并选取高拟合度像素构成每张测试图像中的未知区域。最终，我们提出一种端到端学习框架——已知区域感知域对齐（KRADA），以在区分未知类的同时对齐带标签与未标签开放世界图像中已知类的分布。KRADA的有效性已在两个合成任务和一个COVID-19分割任务中得到验证。