Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual knowledge distillation (MKD), combined with data and feature augmentation. We introduce two auxiliary mean-teacher models based on consistency regularization. More specifically, we use the pseudo-labels generated by a mean teacher to supervise the student network to achieve a mutual knowledge distillation between the two branches. In addition to using image-level strong and weak augmentation, we also discuss feature augmentation. This involves considering various sources of knowledge to distill the student network. Thus, we can significantly increase the diversity of the training samples. Experiments on public benchmarks show that our framework outperforms previous state-of-the-art (SOTA) methods under various semi-supervised settings. Code is available at semi-mmseg.

翻译：一致性正则化在近期半监督语义分割方法中得到了广泛研究，并取得了显著成效。本文提出了一种新的基于数据与特征增强的一致性正则化框架——互知识蒸馏（MKD）。我们引入了两个基于一致性正则化的辅助均值教师模型。具体而言，我们利用均值教师生成的伪标签监督学生网络，从而实现两分支间的互知识蒸馏。除应用图像级别的强、弱增强外，我们还探讨了特征增强方案，通过整合多源知识来蒸馏学生网络，从而显著提升训练样本的多样性。在公开基准上的实验表明，本框架在多种半监督设置下均优于现有最先进（SOTA）方法。代码已开源至semi-mmseg。