arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.06237eess.IVcs.CVcs.LG
收藏

KRADA:语义分割中开集领域自适应的已知区域感知领域对齐

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

Hong Kong Baptist University(香港浸会大学);The University of Melbourne(墨尔本大学);Nanjing University of Science and Technology(南京理工大学);Northeastern University(东北大学);The University of Sydney(悉尼大学)

Chenhong Zhou, Feng Liu, Chen Gong, Rongfei Zeng, Tongliang Liu, William K. Cheung, Bo Han

摘要:

在语义分割中,我们的目标是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,其中标记的训练图像和未标记的测试图像来自相同的分布,并共享相同的标签集。然而,在一个开放的世界中,未标记的测试图像可能包含未知的类别,并有不同的分布从标记的图像。因此,在本文中,我们考虑一个新的,更现实的,更具有挑战性的问题设置,像素级分类器必须用标记图像和未标记的开放世界图像进行训练-我们将其命名为开集域自适应分割(OSDAS)。在OSDAS中,训练好的分类器被期望能够识别未知类像素并很好地分类已知类像素。为了解决OSDAS,我们首先调查未知类像素服从哪个分布。然后,出于拟合优度测试的动机,我们使用统计测量来显示像素如何拟合未知类的分布,并选择高度拟合的像素来形成每个测试图像中的未知区域。最后,我们提出了一个端到端的学习框架,已知区域感知域对齐(KRADA),区分未知类,同时对齐已知类在标记和未标记的开放世界图像中的分布。KRADA的有效性已在两个合成任务和一个COVID-19分割任务上得到验证。

英文摘要:

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.

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。

↑