While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes. In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data. Besides, we also contribute a progressive data augmentation and labeling strategy to facilitate model training with pseudo-labeled data. Experiments on both Cityscapes and PASCAL VOC 2012 datasets demonstrate the effectiveness of our approach. Albeit simple, our method performs favorably in comparison with state-of-the-art approaches. Code will be available at https://github.com/CVMI-Lab/DARS.

本文提出了一种分布对齐与随机采样方法(DARS), 用于生产能够匹配标记数据的真实分类分布的无偏伪标签，同时也提出了一种渐进式数据增强和标签策略，以促进使用伪标签训练模型。实验结果表明，该方法在Cityscapes和PASCAL VOC 2012数据集上的表现优于现有的前沿方法。

基于偏差伪标签的半监督语义分割重分布：基线调查