ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
This addresses the problem of domain shift in 3D object detection for autonomous driving applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles unsupervised domain adaptation for 3D object detection from point clouds by proposing ST3D, a self-training pipeline that uses random object scaling, a quality-aware triplet memory bank, and curriculum data augmentation, achieving state-of-the-art performance and surpassing fully supervised results on the KITTI benchmark.
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.