arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05079cs.CV
收藏

DDS3D:用于半监督3D目标检测的动态阈值密集伪标记

DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection

Huazhong University of Science and Technology(华中科技大学)

Jingyu Li, Zhe Liu, Jinghua Hou, Dingkang Liang

摘要:

在本文中,我们提出了一个简单而有效的半监督三维物体检测器DDS3D。我们的主要贡献有两方面。一方面,与以往使用非最大值抑制(NMS)或其变体来获得稀疏伪标签的方法不同,本文提出了一种密集伪标签生成策略来获得密集伪标签,从而为学生网络保留更多潜在的监督信息。另一方面,本文提出了一种动态阈值的伪标签生成方法,取代了传统的固定阈值方法,保证了整个训练过程中伪标签的质量和数量。受益于这两个组件,我们的DDS 3D优于最先进的半监督3D目标检测,在1%样本的相同配置下,行人的mAP为3.1%,骑自行车的为2.1%。KITTI数据集上的广泛消融研究证明了我们的DDS 3D的有效性。代码和模型将在https://github.com/hust-jy/DDS3D上公开发布

英文摘要:

In this paper, we present a simple yet effective semi-supervised 3D object detector named DDS3D. Our main contributions have two-fold. On the one hand, different from previous works using Non-Maximal Suppression (NMS) or its variants for obtaining the sparse pseudo labels, we propose a dense pseudo-label generation strategy to get dense pseudo-labels, which can retain more potential supervision information for the student network. On the other hand, instead of traditional fixed thresholds, we propose a dynamic threshold manner to generate pseudo-labels, which can guarantee the quality and quantity of pseudo-labels during the whole training process. Benefiting from these two components, our DDS3D outperforms the state-of-the-art semi-supervised 3d object detection with mAP of 3.1% on the pedestrian and 2.1% on the cyclist under the same configuration of 1% samples. Extensive ablation studies on the KITTI dataset demonstrate the effectiveness of our DDS3D. The code and models will be made publicly available at https://github.com/hust-jy/DDS3D

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。

↑