This paper studies semi-supervised learning of semantic segmentation, which
assumes that only a small portion of training images are labeled and the others
remain unlabeled. The unlabeled images are usually assigned pseudo labels to be
used in training, which however often causes the risk of performance
degradation due to the confirmation bias towards errors on the pseudo labels.
We present a novel method that resolves this chronic issue of pseudo labeling.
At the heart of our method lies error localization network (ELN), an auxiliary
module that takes an image and its segmentation prediction as input and
identifies pixels whose pseudo labels are likely to be wrong. ELN enables
semi-supervised learning to be robust against inaccurate pseudo labels by
disregarding label noises during training and can be naturally integrated with
self-training and contrastive learning. Moreover, we introduce a new learning
strategy for ELN that simulates plausible and diverse segmentation errors
during training of ELN to enhance its generalization. Our method is evaluated
on PASCAL VOC 2012 and Cityscapes, where it outperforms all existing methods in
every evaluation setting.

本文提出了一种基于误差定位网络来解决伪标签问题的半监督语义分割方法，该方法有效地消除了训练过程中因使用伪标签带来的性能下降风险，并实现了对不精确伪标签的鲁棒性，同时具有自训练和对比学习的天然集成能力。与现有方法相比，在 PASCAL VOC 2012 和 Cityscapes 数据集上，该方法在所有评估指标中均表现出了卓越的性能。