no code implementations • 14 Oct 2024 • Adam Lilja, Erik Wallin, Junsheng Fu, Lars Hammarstrand
The performance gap to using all labels is reduced from 29. 6 to 3. 4 mIoU on Argoverse, and from 12 to 3. 4 mIoU on NuScenes utilising only 10% of the labelled data.
no code implementations • 24 Mar 2024 • Carl Lindström, Georg Hess, Adam Lilja, Maryam Fatemi, Lars Hammarstrand, Christoffer Petersson, Lennart Svensson
Specifically, we evaluate object detectors and an online mapping model on real and simulated data, and study the effects of different fine-tuning strategies. Our results show notable improvements in model robustness to simulated data, even improving real-world performance in some cases.
1 code implementation • CVPR 2024 • Adam Lilja, Junsheng Fu, Erik Stenborg, Lars Hammarstrand
Specifically, over $80$% of nuScenes and $40$% of Argoverse 2 validation and test samples are less than $5$ m from a training sample.
1 code implementation • ICCV 2023 • Mina Alibeigi, William Ljungbergh, Adam Tonderski, Georg Hess, Adam Lilja, Carl Lindstrom, Daria Motorniuk, Junsheng Fu, Jenny Widahl, Christoffer Petersson
The dataset is composed of Frames, Sequences, and Drives, designed to encompass both data diversity and support for spatio-temporal learning, sensor fusion, localization, and mapping.