Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.
In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation.
#2 best model for Synthetic-to-Real Translation on GTAV-to-Cityscapes Labels
Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.
Domain adaptation is critical for success in new, unseen environments.
Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation.
Hence, we propose a curriculum-style learning approach to minimize the domain gap in urban scenery semantic segmentation.
#6 best model for Synthetic-to-Real Translation on GTAV-to-Cityscapes Labels
We consider the problem of unsupervised domain adaptation in semantic segmentation.
In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems.
#2 best model for Image-to-Image Translation on SYNTHIA Fall-to-Winter