论文标题
取消标签移位的损坏
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
论文作者
论文摘要
现有作品通常将跨域语义分割（CDSS）视为数据分布不匹配问题，并专注于对齐边缘分布或条件分布。但是，不幸的是，标签转移问题被忽略了，实际上通常存在于CDSS任务中，并且经常会导致分类器偏置在学习的模型中。在本文中，我们给出了深入的分析，并表明可以通过对齐数据条件分布并纠正后验概率来克服标签移位的损坏。为此，我们提出了一种新颖的方法来消除CDSS中标签转移问题的损害。在实施中，我们采用类级特征对齐，以进行条件分布对齐，以及两种简单但有效的方法，通过重新恢复分类器预测来纠正从源到目标的分类器偏差。我们在城市场景的基准数据集上进行了广泛的实验，包括GTA5到CityScapes和CityScapes的合成，我们提议的方法在此优于以前的方法，其优势很大。例如，我们配备自训练策略的模型在GTA5上达到59.3％的MIOU到CityScapes，并推向了新的最先进。该代码将在https://github.com/manmanjun/undoing UDA上找到。
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution. However, the label shift issue is unfortunately overlooked, which actually commonly exists in the CDSS task, and often causes a classifier bias in the learnt model. In this paper, we give an in-depth analysis and show that the damage of label shift can be overcome by aligning the data conditional distribution and correcting the posterior probability. To this end, we propose a novel approach to undo the damage of the label shift problem in CDSS. In implementation, we adopt class-level feature alignment for conditional distribution alignment, as well as two simple yet effective methods to rectify the classifier bias from source to target by remolding the classifier predictions. We conduct extensive experiments on the benchmark datasets of urban scenes, including GTA5 to Cityscapes and SYNTHIA to Cityscapes, where our proposed approach outperforms previous methods by a large margin. For instance, our model equipped with a self-training strategy reaches 59.3% mIoU on GTA5 to Cityscapes, pushing to a new state-of-the-art. The code will be available at https://github.com/manmanjun/Undoing UDA.
