SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation

Liang Du, Jingang Tan, Hongye Yang, Jianfeng Feng, Xiangyang Xue, Qibao Zheng, Xiaoqing Ye, Xiaolin Zhang; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 982-991

Abstract


Despite the great success achieved by supervised fully convolutional models in semantic segmentation, training the models requires a large amount of labor-intensive work to generate pixel-level annotations. Recent works exploit synthetic data to train the model for semantic segmentation, but the domain adaptation between real and synthetic images remains a challenging problem. In this work, we propose a Separated Semantic Feature based domain adaptation network, named SSF-DAN, for semantic segmentation. First, a Semantic-wise Separable Discriminator (SS-D) is designed to independently adapt semantic features across the target and source domains, which addresses the inconsistent adaptation issue in the class-wise adversarial learning. In SS-D, a progressive confidence strategy is included to achieve a more reliable separation. Then, an efficient Class-wise Adversarial loss Reweighting module (CA-R) is introduced to balance the class-wise adversarial learning process, which leads the generator to focus more on poorly adapted classes. The presented framework demonstrates robust performance, superior to state-of-the-art methods on benchmark datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Du_2019_ICCV,
author = {Du, Liang and Tan, Jingang and Yang, Hongye and Feng, Jianfeng and Xue, Xiangyang and Zheng, Qibao and Ye, Xiaoqing and Zhang, Xiaolin},
title = {SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}