MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

by   Qiao Wu, et al.

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, MixCycle trained with 10 and achieves a 28.4 labels. Our code will be publicly released.


page 1

page 2

page 3

page 4


An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a cruc...

Unsupervised Learning of Accurate Siamese Tracking

Unsupervised learning has been popular in various computer vision tasks,...

Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking

3D single object tracking is a key task in 3D computer vision. However, ...

SCSS-Net: Superpoint Constrained Semi-supervised Segmentation Network for 3D Indoor Scenes

Many existing deep neural networks (DNNs) for 3D point cloud semantic se...

Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking

3D single object tracking with LiDAR points is an important task in the ...

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Towards 3D object tracking in point clouds, a novel point-to-box network...

Leveraging Shape Completion for 3D Siamese Tracking

Point clouds are challenging to process due to their sparsity, therefore...

Please sign up or login with your details

Forgot password? Click here to reset