Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds is both costly and time-consuming. Inspired by the great success of cycle tracking in unsupervised 2D SOT, we introduce the first semi-supervised approach to 3D SOT. Specifically, we introduce two cycle-consistency strategies for supervision: 1) Self tracking cycles, which leverage labels to help the model converge better in the early stages of training; 2) forward-backward cycles, which strengthen the tracker's robustness to motion variations and the template noise caused by the template update strategy. Furthermore, we propose a data augmentation strategy named SOTMixup to improve the tracker's robustness to point cloud diversity. SOTMixup generates training samples by sampling points in two point clouds with a mixing rate and assigns a reasonable loss weight for training according to the mixing rate. The resulting MixCycle approach generalizes to appearance matching-based trackers. On the KITTI benchmark, based on the P2B tracker [16], MixCycle trained with 10% labels outperforms P2B trained with 100% labels, and achieves a 28.4% precision improvement when using 1% labels. Our code will be released at https://github.com/Mumuqiao/MixCycle.
Athanasios Nenes, Ghislain Gilles Jean-Michel Motos, Paraskevi Georgakaki, Jörg Wieder, Guangyu Li
Isabella Di Lenardo, Paul Robert Guhennec
Athanasios Nenes, Alexis Berne, Satoshi Takahama, Georgia Sotiropoulou, Paraskevi Georgakaki, Romanos Foskinis, Kunfeng Gao, Anne-Claire Marie Billault--Roux