Regularization Strategy for Point Cloud via Rigidly Mixed Sample

02/03/2021
by   Dogyoon Lee, et al.
0

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many studies proposing various augmentation methods for image data. Actually, regularization is essential for point clouds since lack of generality is more likely to occur in point cloud due to small datasets. This paper proposes a Rigid Subset Mix (RSMix), a novel data augmentation method for point clouds that generates a virtual mixed sample by replacing part of the sample with shape-preserved subsets from another sample. RSMix preserves structural information of the point cloud sample by extracting subsets from each sample without deformation using a neighboring function. The neighboring function was carefully designed considering unique properties of point cloud, unordered structure and non-grid. Experiments verified that RSMix successfully regularized the deep neural networks with remarkable improvement for shape classification. We also analyzed various combinations of data augmentations including RSMix with single and multi-view evaluations, based on abundant ablation studies.

READ FULL TEXT

page 1

page 4

page 6

research
12/11/2021

On Automatic Data Augmentation for 3D Point Cloud Classification

Data augmentation is an important technique to reduce overfitting and im...
research
03/12/2023

PointPatchMix: Point Cloud Mixing with Patch Scoring

Data augmentation is an effective regularization strategy for mitigating...
research
10/11/2021

Point Cloud Augmentation with Weighted Local Transformations

Despite the extensive usage of point clouds in 3D vision, relatively lim...
research
02/25/2020

PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

We present PointAugment, a new auto-augmentation framework that automati...
research
09/19/2023

Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptions

Robust 3D perception under corruption has become an essential task for t...
research
03/28/2021

Noise Injection-based Regularization for Point Cloud Processing

Noise injection-based regularization, such as Dropout, has been widely u...
research
05/07/2020

Deep Learning on Point Clouds for False Positive Reduction at Nodule Detection in Chest CT Scans

The paper focuses on a novel approach for false-positive reduction (FPR)...

Please sign up or login with your details

Forgot password? Click here to reset