Bilateral Knowledge Distillation for Unsupervised Domain Adaptation of Semantic Segmentation
Yunnan Wang,Jianxun Li,Yunnan Wang,Jianxun Li
Unsupervised domain adaptation (UDA) aims to learn domain-invariant representations between the labeled source domain and the unlabeled target domain. Existing self- training-based UDA methods use ground truth and pseudo- labels to supervise source data and target data respectively. However, strong supervision in the source domain and pseudo- label noise in the target domain lead to some problems,...
