In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and feature-level perturbations. However, the integration between weak-to-strong consistency regularization and network perturbation has been relatively rare. We note several problems with existing network perturbations in SSS that may contribute to this phenomenon. By revisiting network perturbations, we introduce a new approach for network perturbation to expand the existing weak-to-strong consistency regularization for unlabeled data. Additionally, we present a volatile learning process for labeled data, which is uncommon in existing research. Building upon previous work that includes input-level and feature-level perturbations, we present MLPMatch (Multi-Level-Perturbation Match), an easy-to-implement and efficient framework for semi-supervised semantic segmentation. MLPMatch has been validated on the Pascal VOC and Cityscapes datasets, achieving state-of-the-art performance. Code is available from https://github.com/LlistenL/MLPMatch.

翻译：在半监督语义分割（SSS）中，弱监督到强监督的一致性正则化技术近年来被广泛采用，通常与输入级和特征级扰动相结合。然而，弱监督到强监督一致性正则化与网络扰动之间的结合相对较少。我们指出SSS中现有网络扰动存在的若干问题，这些可能是导致上述现象的原因。通过重新审视网络扰动，我们引入了一种新的网络扰动方法，以扩展现有针对未标记数据的弱监督到强监督一致性正则化框架。此外，我们提出了一种针对标记数据的动态学习过程，这在现有研究中较为罕见。基于先前包含输入级和特征级扰动的研究工作，我们提出了MLPMatch（多级扰动匹配）——一个易于实现且高效的半监督语义分割框架。MLPMatch已在Pascal VOC和Cityscapes数据集上得到验证，并取得了最先进的性能。代码发布于https://github.com/LlistenL/MLPMatch。