Corpus ID: 232168364

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

@article{Yang2021ST3DSF,
  title={ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection},
  author={Jihan Yang and Shaoshuai Shi and Zhe Wang and Hongsheng Li and Xiaojuan Qi},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.05346}
}
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy for mitigating the negative effects of source domain bias. Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 63 REFERENCES
Lyft level 5 perception
  • 2020
Pv-rcnn: Pointvoxel feature set abstraction for 3d object detection
  • In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
  • 2020
Train in Germany, Test in the USA: Making 3D Object Detectors Generalize
  • Yan Wang, X. Chen, +5 authors Wei-Lun Chao
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
Lyft level 5 perception dataset 2020
  • 2019
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
SECOND: Sparsely Embedded Convolutional Detection
Adam: A Method for Stochastic Optimization
From Points to Parts: 3D Object Detection From Point Cloud With Part-Aware and Part-Aggregation Network
Pvrcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection
  • arXiv preprint arXiv:2102.00463,
  • 2021
An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
...
1
2
3
4
5
...