Unsupervised Domain Adaptation for Semantic Segmentation
A Survey
Public Leaderboard
Get an overview about all unsupervised domain adaptation methods for semantic segmentation. We will update the leaderboard every month with the latest papers.
Plots
Analyze the progress of unsupervised domain adaptation using interactive plots with detailed information for each of the papers.
Paper
Check out our survey paper for more details.
Contribute
If you want your own new paper to be shown on this website please open an issue in our Github Repo. Also, our database might contain some mistakes or gaps (i.e. regarding conferences). Please also open an issue if you spot a mistake so that we can correct it.
Unsupervised Domain Adaptation for Semantic Segmentation
Unsupervised Domain Adaptation (UDA) is one of the most important ways to improve the generalization of Deep Neural Networks (DNNs) and an entire research area emerged. With this survey we review the state-of-the-art research in the area of unsupervised domain adaptation for semantic segmentation for the synthetic-to-real domain shift. This project website contains both an up-to-date leaderboard and interactive plots to analyze the progress and methods of UDA for semantic segmentation.
Figure: Principle of Unsupervised Domain Adaptation for Semantic Segmentation.