no code implementations • 9 Feb 2024 • Fengyi Shen, Li Zhou, Kagan Kucukaytekin, Ziyuan Liu, He Wang, Alois Knoll
Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers.
no code implementations • 6 Nov 2023 • Zador Pataki, Mohammad Altillawi, Menelaos Kanakis, Rémi Pautrat, Fengyi Shen, Ziyuan Liu, Luc van Gool, Marc Pollefeys
Our proposed method enhances cross-domain localization performance, significantly reducing the performance gap.
1 code implementation • CVPR 2023 • Fengyi Shen, Akhil Gurram, Ziyuan Liu, He Wang, Alois Knoll
Domain adaptive semantic segmentation methods commonly utilize stage-wise training, consisting of a warm-up and a self-training stage.
1 code implementation • 21 Nov 2022 • Fengyi Shen, Zador Pataki, Akhil Gurram, Ziyuan Liu, He Wang, Alois Knoll
In this paper, we propose LoopDA for domain adaptive nighttime semantic segmentation.
1 code implementation • 30 Nov 2021 • Fengyi Shen, Akhil Gurram, Ahmet Faruk Tuna, Onay Urfalioglu, Alois Knoll
Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation.
1 code implementation • 22 Mar 2021 • Akhil Gurram, Ahmet Faruk Tuna, Fengyi Shen, Onay Urfalioglu, Antonio M. López
In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision.