Survey of unsupervised segmentation in new domains for autonomous driving
Survey of unsupervised segmentation in new domains for autonomous driving
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving
arXiv paper abstract https://arxiv.org/abs/2304.11928
arXiv PDF paper https://arxiv.org/pdf/2304.11928.pdf
Project page https://uda-survey.github.io/survey/leaderboard
Deep neural networks (DNNs) … play a significant role in … automated driving and are employed for tasks such as detection, semantic segmentation, and sensor fusion.
… generalization of DNNs to new … domains is a major problem … methods are required to adapt … to new domains without labeling … The task … is termed unsupervised domain adaptation (UDA).
… the shift between synthetic and real data is of … importance for automated driving, as it allows the use of simulation environments for DNN training.
… present an overview of the current state of the art in this field of research.
… categorize and explain the different approaches for UDA. The number of considered publications is larger than any other survey on this topic.
… present a quantitative comparison of the approaches and use the observations to point out the latest trends in this field …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
