Das Paper mit dem Titel „Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation“ von Stephan Brehm, Sebastian Scherer und Rainer Lienhart wurde auf der Internatial Conference on Agents and Artificial Intelligence (ICAART) 2022 veröffentlicht. In diesem Paper stellen die Autoren eine Methode vor, mit welcher Bildsegmentierung von realen Bildern aus synthetischen Daten eines Simulators gelernt werden kann.

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target
domain where no labelled data is available. In this work, we investigate the problem of UDA from a
synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation.
We propose a semantically consistent image-to-image translation method in combination with a consistency
regularisation method for UDA. We overcome previous limitations on transferring synthetic images to
real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation
model that receives additional feedback from semantic labels on both domains. Our method outperforms
state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant
domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.