Publications
MixCycle: Mixup Assisted Semi-Supervised 3D Single Object
Tracking with Cycle Consistency, ICCV 2023 We propose the first semi-supervised approach to 3D Single Object Tracking. Our method, MixCycle, uses self and forward-backward cycle-consistency for supervision, and introduce a data augmentation strategy named SOTMixup to improve the tracker's robustness to point cloud diversity. It is generalizes to appearance matching-based trackers. paper / bibtex / code |