论文标题
不受监督的域适应性，并具有隐式伪监督的语义细分
Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation
论文作者
论文摘要
伪标志性是用于语义分割的未加工域适应性中的一种流行技术。但是，伪标签是嘈杂的，由于源和目标域和训练过程之间的差异，因此不可避免地存在确认偏差。在本文中，我们通过伪标签训练该模型，这些标签本身是为了学习有关目标域的新互补知识。具体来说，我们提出了一个三学习架构，每个两个分支都会产生伪标签来训练第三个标签。并且我们根据每个两个分支的概率分布的相似性对齐伪标签。为了进一步隐式使用伪标签，我们最大程度地提高了不同类别的特征距离，并通过三重态损失最大程度地减少了同一类的距离。对GTA5进行的广泛实验，对城市景观和CityScapes任务的合成，表明该方法有很大的改进。
Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and training process. In this paper, we train the model by the pseudo labels which are implicitly produced by itself to learn new complementary knowledge about target domain. Specifically, we propose a tri-learning architecture, where every two branches produce the pseudo labels to train the third one. And we align the pseudo labels based on the similarity of the probability distributions for each two branches. To further implicitly utilize the pseudo labels, we maximize the distances of features for different classes and minimize the distances for the same classes by triplet loss. Extensive experiments on GTA5 to Cityscapes and SYNTHIA to Cityscapes tasks show that the proposed method has considerable improvements.
