DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

Oct 23, 2022·
Xin Lai
,
Zhuotao Tian
,
Xiaogang Xu
Ying-Cong Chen
Ying-Cong Chen
,
Shu Liu
,
Hengshuang Zhao
,
Liwei Wang
,
Jiaya Jia
· 0 min read
Abstract
Unsupervised domain adaptation in semantic segmentation alleviates the reliance on expensive pixel-wise annotation. It uses a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet to alleviate source domain overfitting and let the final model focus more on the segmentation task. Also, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods. Extensive ablation studies verify the effectiveness of each component.
Type
Publication
Proceedings of the European conference on computer vision (ECCV)