半监督语义分割中的相互知识蒸馏
Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation
AI总结：
提出一种结合数据与特征增强的相互知识蒸馏框架，通过两个平均教师模型生成伪标签监督学生网络，在多种半监督设置下超越现有最先进方法。
摘要：
一致性正则化在近年来的半监督语义分割方法中已被广泛研究，并取得了令人瞩目的性能。在这项工作中，我们提出了一种新的一致性正则化框架，称为相互知识蒸馏（MKD），并结合了数据和特征增强。我们引入了两个基于一致性正则化的辅助平均教师模型。更具体地说，我们利用一个平均教师生成的伪标签来监督学生网络，以实现两个分支之间的相互知识蒸馏。除了使用图像级别的强和弱增强外，我们还讨论了特征增强。这涉及考虑各种知识来源来蒸馏学生网络。因此，我们可以显著增加训练样本的多样性。在公共基准上的实验表明，我们的框架在各种半监督设置下优于先前的最先进（SOTA）方法。代码可在semi-mmseg获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
