Content Disentanglement for Semantically Consistent Synthetic-to-Real Domain Adaptation
This work addresses domain adaptation for autonomous driving, but it appears incremental as it builds on existing methods to improve semantic consistency.
The paper tackled the problem of semantic inconsistencies in synthetic-to-real domain adaptation for autonomous driving perception, achieving semantically consistent image transfer through a novel unsupervised network architecture.
Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthetic data encounter serious performance drops when they are tested on real data. Such performance drops are commonly attributed to the domain gap between real and synthetic data. Domain adaptation methods that have been applied to mitigate the aforementioned domain gap achieve visually appealing results, but usually introduce semantic inconsistencies into the translated samples. In this work, we propose a novel, unsupervised, end-to-end domain adaptation network architecture that enables semantically consistent \textit{sim2real} image transfer. Our method performs content disentanglement by employing shared content encoder and fixed style code.