arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05346cs.CVcs.LG
收藏

ST3D:三维目标检测中无监督领域自适应的自训练

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

The University of Hong Kong(香港大学);CUHK-SenseTime Joint Laboratory(香港中文大学-商汤科技联合实验室);The Chinese University of Hong Kong(香港中文大学);SenseTime Research(商汤科技研究院);Shanghai AI Laboratory(上海人工智能实验室);School of CST Xidian University(西安电子科技大学计算机科学与技术学院)

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

摘要:

我们提出了一个新的域自适应自训练管道,命名为ST3D,用于从点云进行3D目标检测的无监督领域自适应。首先,我们用我们提出的随机对象缩放策略在源域上预训练3D检测器,以减轻源域偏差的负面影响。然后,通过交替进行两个步骤来迭代地改进检测器,这两个步骤是使用开发的质量感知三元组存储体的伪标签更新和使用课程数据增强的模型训练。这些用于3D目标检测的特定设计使检测器能够使用一致且高质量的伪标签进行训练,并避免过度拟合伪标签数据中的大量简单示例。我们的ST3D在所有评估的数据集上都达到了最先进的性能,甚至超过了KITTI 3D目标检测基准测试的完全监督结果。代码将在https://github.com/CVMI-Lab/ST3D上提供。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑