PointCutMix: Regularization Strategy for Point Cloud Classification

5 Jan 2021  ·  Jinlai Zhang, Lyujie Chen, Bo Ouyang, Binbin Liu, Jihong Zhu, Yujing Chen, Yanmei Meng, Danfeng Wu ·

As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent. In this paper, we propose a simple and effective augmentation method for the point cloud data, named PointCutMix, to alleviate those problems. It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs. Two replacement strategies are proposed to adapt to the accuracy or robustness requirement for different tasks, one of which is to randomly select all replacing points while the other one is to select k nearest neighbors of a single random point. Both strategies consistently and significantly improve the performance of various models on point cloud classification problems. By introducing the saliency maps to guide the selection of replacing points, the performance further improves. Moreover, PointCutMix is validated to enhance the model robustness against the point attack. It is worth noting that when using as a defense method, our method outperforms the state-of-the-art defense algorithms. The code is available at:https://github.com/cuge1995/PointCutMix

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Point Cloud Classification ModelNet40 PointCutmix Overall Accuracy 93.4 # 52
3D Point Cloud Classification ModelNet40-C DGCNN+PointCutMix-R Error Rate 0.173 # 3
3D Point Cloud Classification ModelNet40-C PointNet++/+PointCutMix-R Error Rate 0.191 # 5

Methods


No methods listed for this paper. Add relevant methods here