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

By Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi. 2021

240 citations recorded by the source corpus.

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 bank and the model training with curriculum data augmentation. These specific designs for 3D object detection enable the detector to be trained with consistent and high-quality pseudo labels and to avoid overfitting to the large number of easy examples in pseudo labeled data. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark. Code will be available at https://github.com/CVMI-Lab/ST3D.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Xiaodan Liang
  2. Hang Xu
  3. Zhenguo Li
  4. Wei Zhang
  5. Mingkui Tan
  6. Shuaicheng Niu
  7. Chuang Gan
  8. Yifan Zhang

In Computer Vision and Pattern Recognition

  1. Xiaodan Liang
  2. Zhenguo Li
  3. Hang Xu
  4. Mingkui Tan
  5. Wei Zhang
  6. Chuang Gan
  7. Chunjing Xu
  8. Yifan Zhang

Citations in the corpus