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：在语义分解中,我们的目标是训练一个像素级分类器, 将标签培训图像和未贴标签的测试图像来自相同的分布和共享标签组。 然而, 在开放的世界上, 未贴标签的测试图像可能包含未知的类别, 并且与标签的图像有不同的分布。 因此, 在本文件中, 我们考虑一个新的、 更现实和更具挑战性的问题设置, 像素级分类器必须用标签图像和未贴标签的开放世界图像来培训所有像素的分类标签, 我们命名它为开放的域调整部分( OSDASAS)。 在 OSDASS, 训练有素的分类师预计将识别未知的类像素, 并对已知的类像素进行分类分类。 为了解决 OSDSDS, 我们首先调查未知的类像素所服从的分布。 然后, 我们用统计测量来显示像素如何适合未知的类和未贴近的合成像素, 并选择了高度适合的像素, 以形成未知的区域( KARDA 校验的校准等级), 最后我们提议一个最终在未知的区域里, 校正的等级上, 。