1. 四个问题

解决什么问题
在点云引入一种数据增强方式
用什么方法解决
mixup结合点云
效果如何
提升1-2点，在数据量小提点明显
还存在什么问题
？

2. 论文内容

Abstract

本篇论文介绍了用实例间插值法对点云进行数据增强的方法。插值数据增强是图像领域中一种简单有效的方法。然而，这样的混合不能直接转移到点云，因为我们在两个不同对象的点之间没有一对一的对应关系。本篇论文将点云间的数据增强定义为最短路径线性插值。为此，我们引入了PointMixup。这种插值方法通过两个点云之间的路径函数优化分配来生成新的示例。我们证明了我们的PointMixup能够在两个点云之间找到最短路径，并且插值属于赋值不变的和线性的。PointMixup允许在点云域引入基于插值的强正则化器。在实验中，我们展示了PointMixup在点云分类中的潜力，特别是在缺乏实例的情况下，我们同时展示了PointMixup在增强应对噪点和点的几何变换方面的鲁棒性。

1 Introduction

mixup能够提高模型的正则化和泛化能力，例如以下工作

Several works have shown that generating new training examples, by interpolating images and their corresponding labels, leads to improved network regularization and generalization, e.g., [8, 24, 34, 26]

mixup在图像领域应用容易，将mixup应用到点云的难点：没有一一对应的坐标（2D图像上有，例如每个像素点对应和label对应）

Such a mixup is feasible in the image domain, due to the regular structure of images and one-to-one correspondences between pixels. However, this setup does not generalize to the point cloud domain, since there is no one-to-one correspondence and ordering between points.

2 Related Work

Deep learning for point clouds.
PointNet++ 多层次是个关键（trick）

PointNet++ [16] extends this idea further with hierarchical structure by relying on a heuristic method of farthest point sampling and grouping to build the hierarchy.

mixup是个模型无关的方法，是一种数据增强，简单有效，能够减少泛化误差。

To that end, we propose a new model-agnostic data augmentation. We propose a Mixup regularization for point clouds and show that it can build on various architectures to obtain better classification results by reducing the generalization error in classification tasks.

最相关的工作：Li et al. [11]

A very recent work by Li et al. [11] also considers improving point cloud classification by augmentation. They rely on auto-augmentation and a complicated adversarial training procedure, whereas in this work we propose to augment point clouds by interpolation.

Interpolation-based regularization.
使用正则化方法有利于提高泛化能力，这在深度学习中已经成为标准做法

Employing regularization approaches for training deep neural networks to improve their generalization performances have become standard practice in deep learning.

Mixup 和 Manifold Mixup

Recent works consider a regularization by interpolating the example and label pairs, commonly known as Mixup [24, 8, 34]. Manifold Mixup [26] extends Mixup by interpolating the hidden representations at multiple layers.