Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imblance

04/08/2019
by   David Griffiths, et al.
0

Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the natural class im-balance observed in nature. For example, a 3D scan of an urban environment will consist mostly of road and facade, whereas other objects such as poles will be under-represented. In this paper we address this issue by employing a weighted augmentation to increase classes that contain fewer points. By mitigating the class im-balance present in the data we demonstrate that a standard PointNet++ deep neural network can achieve higher performance at inference on validation data. This was observed as an increase of F1 score of 19 Semantic3D respectively where no class im-balance pre-processing had been performed. Our networks performed better on both highly-represented and under-represented classes, which indicates that the network is learning more robust and meaningful features when the loss function is not overly exposed to only a few classes.

READ FULL TEXT
research
04/08/2019

Weighted Point Cloud Augmentation for Neural Network Training Data Class-Imbalance

Recent developments in the field of deep learning for 3D data have demon...
research
03/12/2023

PointPatchMix: Point Cloud Mixing with Patch Scoring

Data augmentation is an effective regularization strategy for mitigating...
research
04/13/2023

PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmark

Point clouds offer comprehensive and precise data regarding the contour ...
research
05/23/2017

Classification of Aerial Photogrammetric 3D Point Clouds

We present a powerful method to extract per-point semantic class labels ...
research
07/30/2021

Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport

Good quality reconstruction and comprehension of a scene rely on 3D esti...
research
09/25/2015

Deep Multimodal Embedding: Manipulating Novel Objects with Point-clouds, Language and Trajectories

A robot operating in a real-world environment needs to perform reasoning...

Please sign up or login with your details

Forgot password? Click here to reset