Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Ruifei He, Jihan Yang, Xiaojuan Qi• 2021

Related benchmarks

TaskDatasetResultRank
Semantic segmentationPASCAL VOC 2012
mIoU73.89
187
3D Semantic SegmentationScribbleKITTI (val)
mIoU60.8
9
Showing 2 of 2 rows

Other info

Follow for update