Knowledge representation learning (KRL) has been used in plenty of knowledge-driven tasks.
In order to take advantage of the most effective gradient-based attack, a differentiable sample module that back-propagate the gradient of point cloud to mesh is introduced.
Some deep neural networks are invariant to some input transformations, such as Pointnet is permutation invariant to the input point cloud.
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.
Ranked #2 on 3D Point Cloud Classification on ModelNet40-C