Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation.

翻译：在半监督的语义分解学习中,Psedo监督被视为核心理念,而且,在只使用高质量假标签和利用所有假标签之间总是存在着一种权衡。我们提出一种新的学习方法,称为保守-进步合作学习(CPCL),其中两个预测网络同时接受培训,根据两种预测的一致和分歧执行假监督。一个网络通过交叉监督寻求共同点,并受到高质量标签的监督,以确保更可靠的监督,而另一个网络则通过工会监督保留差异,并接受所有假标签的监督,以继续以好奇心探险。因此,保守的演变和渐进探索可以实现。为了减少可疑假标签的影响,损失根据预测的信心进行动态重估。广泛的实验表明,CPL在半监督的语义分解方面实现了最先进的表现。