PointDrop: Improving Object Detection from Sparse Point Clouds via Adversarial Data Augmentation

Ma, Wenxin; Chen, Jian; Du, Qing; Jia, Wei

doi:10.1109/icpr48806.2021.9412691

Cited by 7 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To increase the flexibility of data augmentation, some researchers [2,12] use optimistic strateties to automate relative hyperparameters. Adversarial learning can also be employed to adjust the difficulty of training samples during training to improve model robustness [14]. In GT-sample [20], the author created a database for the information of all groundtruths.…”

Section: Introductionmentioning

confidence: 99%

Pattern-Aware Data Augmentation for LiDAR 3D Object Detection

Waslander

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data. As a widely used data augmentation method, GT-sample effectively improves detection performance by inserting groundtruths into the lidar frame during training. However, these samples are often placed in unreasonable areas, which misleads model to learn the wrong context information between targets and backgrounds. To address this problem, in this paper, we propose a context-aware data augmentation method (CA-aug) , which ensures the reasonable placement of inserted objects by calculating the "Validspace" of the lidar point cloud. CA-aug is lightweight and compatible with other augmentation methods. Compared with the GT-sample and the similar method in Lidar-aug(SOTA), it brings higher accuracy to the existing detectors. We also present an indepth study of augmentation methods for the range-view-based(RVbased) models and find that CA-aug can fully exploit the potential of RV-based networks. The experiment on KITTI val split shows that CA-aug can improve the mAP of the test model by 8%.

show abstract