arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.09446cs.CV
收藏

面向3D目标检测的密度不敏感无监督域适应

Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection

Peking University(北京大学)

Qianjiang Hu, Daizong Liu, Wei Hu

AI总结:

针对点云3D检测中LiDAR光束密度造成的域间差异,提出结合RBRS、师生伪标签与OGA跨密度一致性的无监督域适应框架,并在三个数据集上取得SOTA性能。

摘要:

基于点云的3D目标检测在安全攸关的自动驾驶中至关重要。尽管许多工作已在该任务上付出巨大努力并取得显著进展,但由于域间差异,其中大多数方法都面临标注成本高昂以及向未知数据迁移能力较差的问题。近来,少数工作尝试解决目标层面的域间差异,但仍无法适应两个域之间变化的光束密度差异,而这一差异对于缓解LiDAR采集设备的特性差别十分关键。为此,我们尝试提出一种密度不敏感的域适应框架,以解决由密度引发的域间差异。具体而言,我们首先引入Random Beam Re-Sampling(RBRS,随机光束重采样),以增强在源域上训练的3D检测器对变化光束密度的鲁棒性。随后,我们将这一预训练检测器作为骨干模型,并把无标注目标域数据输入我们新设计的特定任务师生框架,以预测其高质量伪标签。为了进一步将密度不敏感特性适应到目标域,我们向教师分支和学生分支输入同一样本的不同密度版本,并提出Object Graph Alignment(OGA,目标图对齐)模块,在两个分支之间构建两个目标图,以强化跨密度目标在属性与关系上的一致性。在三个广泛采用的3D目标检测数据集上的实验结果表明,我们提出的域适应方法优于最先进方法,尤其是在变密度数据上。代码可在https://github.com/WoodwindHu/DTS获取。

英文摘要:

3D object detection from point clouds is crucial in safety-critical autonomous driving. Although many works have made great efforts and achieved significant progress on this task, most of them suffer from expensive annotation cost and poor transferability to unknown data due to the domain gap. Recently, few works attempt to tackle the domain gap in objects, but still fail to adapt to the gap of varying beam-densities between two domains, which is critical to mitigate the characteristic differences of the LiDAR collectors. To this end, we make the attempt to propose a density-insensitive domain adaption framework to address the density-induced domain gap. In particular, we first introduce Random Beam Re-Sampling (RBRS) to enhance the robustness of 3D detectors trained on the source domain to the varying beam-density. Then, we take this pre-trained detector as the backbone model, and feed the unlabeled target domain data into our newly designed task-specific teacher-student framework for predicting its high-quality pseudo labels. To further adapt the property of density-insensitivity into the target domain, we feed the teacher and student branches with the same sample of different densities, and propose an Object Graph Alignment (OGA) module to construct two object-graphs between the two branches for enforcing the consistency in both the attribute and relation of cross-density objects. Experimental results on three widely adopted 3D object detection datasets demonstrate that our proposed domain adaption method outperforms the state-of-the-art methods, especially over varying-density data. Code is available at https://github.com/WoodwindHu/DTS}{https://github.com/WoodwindHu/DTS.

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。

↑