We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive property among different pixels. We leverage the pixel-level L2 loss and the pixel contrastive loss for the two purposes respectively. To address the computational efficiency issue and the false negative noise issue involved in the pixel contrastive loss, we further introduce and investigate several negative sampling techniques. Extensive experiments demonstrate the state-of-the-art performance of our method (PC2Seg) with the DeepLab-v3+ architecture, in several challenging semi-supervised settings derived from the VOC, Cityscapes, and COCO datasets.

翻译：我们提出了一种新型的半监督的语义分解方法,它共同实现了两种分解模型规律的分解分解:图像放大和不同像素间地-空间对比特性之间的标签-空间一致性属性;我们利用像素水平L2损失和像素对比性损失分别用于两个目的;为了解决计算效率问题和像素对比损失所涉的虚假负面噪音问题,我们进一步引入并调查了几种负面取样技术。广泛的实验展示了我们与DeepLab-V3+结构在由VOC、Cityscaps和COCO数据集产生的若干具有挑战性的半监督环境中最先进的方法(PC2Seg)的性能。