Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

Understand

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.