arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.13428cs.CV
收藏

PseudoAugment:学习使用未标记数据进行点云数据增强

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

Waymo(Waymo公司);Google(谷歌)

Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang, Xiao Zhang, Jonathon Shlens, Mingxing Tan, Dragomir Anguelov

摘要:

数据增强是点云数据三维检测中提高数据利用率、节省标注成本的重要技术。然而,到目前为止,现有的增强策略被设计为仅利用标记数据,这限制了数据的多样性。在本文中,我们认识到伪标记和数据增强是互补的,因此提出利用未标记的数据进行数据增强,以丰富训练数据。特别是,我们设计了三种新的基于伪标签的数据增强策略(PseudoAugments)来融合标记和伪标记的场景,包括帧(PseudoFrame),对象(PseudoBBox)和背景(PseudoBackground)。通过减少伪标记错误和生成不同的融合训练场景,伪增强优于伪标记。我们展示了基于点和基于体素的架构,不同的模型容量以及KITTI和Waymo开放数据集的伪增强。为了减轻超参数调整和迭代伪标记的成本,我们开发了一个基于人口的数据增强框架的三维检测,名为AutoPseudoAugment。与以前离线执行伪标记的工作不同,我们的框架一次性执行伪增广和超参数调整,以降低计算成本。在大规模Waymo开放数据集上的实验结果表明,我们的方法优于最先进的自动数据增强方法(PPBA)和自训练方法(伪标签)。特别地,与现有技术相比,AutoPseudoAugment在车辆和行人任务上的数据效率约为3倍和2倍。值得注意的是,AutoPseudoAugment几乎匹配完整的数据集训练结果,在车辆检测任务中只有10%的标记运行段。

英文摘要:

Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been designed to only utilize labeled data, which limits the data diversity. In this paper, we recognize that pseudo labeling and data augmentation are complementary, thus propose to leverage unlabeled data for data augmentation to enrich the training data. In particular, we design three novel pseudo-label based data augmentation policies (PseudoAugments) to fuse both labeled and pseudo-labeled scenes, including frames (PseudoFrame), objecta (PseudoBBox), and background (PseudoBackground). PseudoAugments outperforms pseudo labeling by mitigating pseudo labeling errors and generating diverse fused training scenes. We demonstrate PseudoAugments generalize across point-based and voxel-based architectures, different model capacity and both KITTI and Waymo Open Dataset. To alleviate the cost of hyperparameter tuning and iterative pseudo labeling, we develop a population-based data augmentation framework for 3D detection, named AutoPseudoAugment. Unlike previous works that perform pseudo-labeling offline, our framework performs PseudoAugments and hyperparameter tuning in one shot to reduce computational cost. Experimental results on the large-scale Waymo Open Dataset show our method outperforms state-of-the-art auto data augmentation method (PPBA) and self-training method (pseudo labeling). In particular, AutoPseudoAugment is about 3X and 2X data efficient on vehicle and pedestrian tasks compared to prior arts. Notably, AutoPseudoAugment nearly matches the full dataset training results, with just 10% of the labeled run segments on the vehicle detection task.

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。

↑