Semantic segmentation via domain adaptation with global structure embedding

Tianyi Zhang, Guosheng Lin, Jianfei Cai, Alex C. Kot

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)


In this paper we focus on the problem of unsupervised domain adaptation for semantic segmentation. The previous works usually focus on adversarial learning either in pixel-level or feature-level. However, global structure knowledge is often neglected in the adversarial learning due to the possible reasons: First, the result of pixel-level adversarial learning does not necessarily preserve the semantic consistency of the input image. Second, global structure knowledge is not embedded to regularize the feature-level adversarial learning. In this work, we propose a framework for unsupervised domain adaptation in semantic segmentation which effectively incorporates pixel-level, feature-level adversarial learning and self-Training strategy. Our framework embeds the global structure knowledge into the adversarial training step to tackle the problem of structure misalignment. Consequently, our proposed framework achieves the state-of-The-Art semantic segmentation domain adaptation results on the task of transferring GTA5 to Cityscapes.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Visual Communications and Image Processing (VCIP 2019)
EditorsMark Pickering, Qiang Wu, Lei Wang, Jiaying Liu
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9781728137230
ISBN (Print)9781728137247
Publication statusPublished - 2019
Externally publishedYes
EventIEEE Visual Communications and Image Processing 2019 - Sydney, Australia
Duration: 1 Dec 20194 Dec 2019 (Proceedings)


ConferenceIEEE Visual Communications and Image Processing 2019
Abbreviated titleVCIP 2019
Internet address


  • domain adaptation
  • semantic segmentation

Cite this