PointCutMix: Regularization Strategy for Point Cloud Classification

01/05/2021 ∙ by Jinlai Zhang, et al. ∙ 0

3D point cloud analysis has received increasing attention in recent years, however, the diversity and availability of point cloud datasets are still limited. We therefore present PointCutMix, a simple but effective method for augmentation in point cloud. In our method, after finding the optimal assignment between two point clouds, we replace some points in one point cloud by its counterpart point in another point cloud. Our strategy consistently and significantly improves the performance across various models and datasets. Surprisingly, when it is used as a defense method, it shows far superior performance to the SOTA defense algorithm. The code is available at:https://github.com/cuge1995/PointCutMix

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

Code Repositories

PointCutMix

our code will be coming soon


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.