Re-Distributing Biased Pseudo Labels for Semi-Supervised Semantic Segmentation: A Baseline Investigation

Ruifei He, Jihan Yang, Xiaojuan Qi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 6930-6940

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2021_ICCV, author = {He, Ruifei and Yang, Jihan and Qi, Xiaojuan}, title = {Re-Distributing Biased Pseudo Labels for Semi-Supervised Semantic Segmentation: A Baseline Investigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {6930-6940} }