Can I read ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection on EtoBox?

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection by Yang, Jihan; Shi, Shaoshuai; Wang, Zhe; Li, Hongsheng; Qi, Xiaojuan is a scholarly article available to read on EtoBox.

What is ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection about?

In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as alleviating the negative impacts of noisy pseudo labels on model training. First, ST3D++ pre-trains the 3D object detector on the labeled source domain with random object scaling (ROS) which is designed to reduce target domain pseudo label noise arising from object scale bias of the source domain. Then, the detector is progressively improved through alternating between generating pseudo labels and training the object detector with pseudo-labeled target domain data. Here, we equip the pseudo label generation process with a hybrid quality-aware triplet memory to improve the quality and stability of generated pseudo labels. Meanwhile, in the model training stage, we propose a source data assisted training strategy and a curriculum data augmentation policy to effectively rectify noisy gradient directions and avoid model over-fitting to noisy pseudo labeled data. These specific designs enable the detector to be trained on meticulously refined pseudo la

Author

Yang, Jihan; Shi, Shaoshuai; Wang, Zhe; Li, Hongsheng; Qi, Xiaojuan

Published

2021

Language

EN