arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00182cs.CVcs.AI
收藏

基于时间图神经网络的半监督三维目标检测

Semi-supervised 3D Object Detection via Temporal Graph Neural Networks

Carnegie Mellon University(卡内基梅隆大学);Honda Research Institute(本田研究所);National Yang Ming Chiao Tung University(国立阳明交通大学)

Jianren Wang, Haiming Gang, Siddharth Ancha, Yi-Ting Chen, David Held

摘要:

3D目标检测在自动驾驶和其他机器人应用中起着重要作用。然而,这些检测器通常需要在大量的注释数据上进行训练,这是昂贵且耗时的。相反,我们建议通过时间图神经网络对3D对象检测器进行半监督学习来利用大量未标记的点云视频。我们的见解是,时间平滑可以在未标记的数据上创建更准确的检测结果,然后可以使用这些平滑的检测来重新训练检测器。我们学习使用图神经网络来执行这种时间推理,其中边缘表示不同时间帧中候选检测之间的关系。经过半监督学习后,与在相同数量的标记数据上训练的基线相比,我们的方法在具有挑战性的nuScenes和H3D基准上实现了最先进的检测性能。项目和代码在https://www.jianrenw.com/SOD-TGNN/上发布。

英文摘要:

3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this temporal reasoning with a graph neural network, where edges represent the relationship between candidate detections in different time frames. After semi-supervised learning, our method achieves state-of-the-art detection performance on the challenging nuScenes and H3D benchmarks, compared to baselines trained on the same amount of labeled data. Project and code are released at https://www.jianrenw.com/SOD-TGNN/.

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。

↑