D
Dengxin Dai
Researcher at ETH Zurich
Publications - 180
Citations - 6923
Dengxin Dai is an academic researcher from ETH Zurich. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 31, co-authored 144 publications receiving 3854 citations. Previous affiliations of Dengxin Dai include Wuhan University & Max Planck Society.
Papers
More filters
Proceedings ArticleDOI
Domain Adaptive Faster R-CNN for Object Detection in the Wild
TL;DR: Zhang et al. as discussed by the authors designed two domain adaptation components, on image level and instance level, to reduce the domain discrepancy in Faster R-CNN, which is based on $$-divergence theory and is implemented by learning a domain classifier in adversarial training manner.
Journal ArticleDOI
Semantic Foggy Scene Understanding with Synthetic Data
TL;DR: In this paper, a semi-supervised learning strategy was proposed for semantic foggy scene understanding, which combines supervised learning with an unsupervised supervision transfer from clear-weather images to their synthetic foggy counterparts.
Posted Content
Domain Adaptive Faster R-CNN for Object Detection in the Wild
TL;DR: Zhang et al. as discussed by the authors designed two domain adaptation components, on image level and instance level, to reduce the domain discrepancy in Faster R-CNN, which is based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner.
Journal ArticleDOI
Semantic Foggy Scene Understanding with Synthetic Data
TL;DR: In this article, a semi-supervised learning strategy was proposed for semantic foggy scene understanding, which combines supervised learning with an unsupervised supervision transfer from clear-weather images to their synthetic foggy counterparts.
Journal ArticleDOI
Multi-Task Learning for Dense Prediction Tasks: A Survey.
Simon Vandenhende,Stamatios Georgoulis,Wouter Van Gansbeke,Marc Proesmans,Dengxin Dai,Luc Van Gool +5 more
TL;DR: This survey provides a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision, explicitly emphasizing on dense prediction tasks.