In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. We propose a novel consistency regularization approach, called cross pseudo supervision (CPS). Our approach imposes the consistency on two segmentation networks perturbed with different initialization for the same input image. The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012. Code is available at https://git.io/CPS.

翻译：在本文中,我们通过探索标签数据和额外无标签数据来研究半监督的语义分解问题。我们提出了一种新的一致性规范化方法,称为交叉伪监管(CPS ) 。我们的方法要求两个与同一输入图像不同初始化相交的分解网络的一致性。一个环形分解网络输出的假单热标签图用于监督带有标准交叉机能损失的其他分解网络,反之亦然。CPS 的连贯性有两个作用:鼓励两种互扰网络对同一输入图像的预测高度相似性,并通过使用非标签数据与伪标签扩大培训数据。实验结果显示,我们的方法在城市景区和PACAL VOC 2012 上达到了最先进的半监督分解性表现。 代码可在 https://git.io/CPS 上查阅 。