Synthetic data find application in computer vision tasks for a long time. Limited performance of algorithms trained solely on synthetic data has been approached with domain adaptation techniques such as the ones based on generative adversarial framework [1]. In this work we demonstrate how using adversarial training alone can introduce semantic inconsistencies in refined images. We suggest leveraging available semantic labels from target domain using naive re-sampling approach alongside with adversarial loss. We also show that aforementioned strategy improves quality of translated images of underlying method and their usability for the semantic segmentation task in the context of autonomous driving. This method will be also put in comparison with existing state-of-the-art synthetic to real domain adaptation methods.
Sampling/Importance Resampling for Semantically Consistent Synthetic to Real Image Domain Adaptation in Urban Traffic Scenes
2019 IEEE Intelligent Vehicles Symposium (IV) ; 1061-1068
2019-06-01
3795170 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch