SageMix: Saliency-Guided Mixup for Point Clouds

10/13/2022
by   Sanghyeok Lee, et al.
0

Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity. Also, recent studies of saliency-aware Mixup in the image domain show that preserving discriminative parts is beneficial to improving the generalization performance. However, these Mixup-based data augmentations are underexplored in 3D vision, especially in point clouds. In this paper, we propose SageMix, a saliency-guided Mixup for point clouds to preserve salient local structures. Specifically, we extract salient regions from two point clouds and smoothly combine them into one continuous shape. With a simple sequential sampling by re-weighted saliency scores, SageMix preserves the local structure of salient regions. Extensive experiments demonstrate that the proposed method consistently outperforms existing Mixup methods in various benchmark point cloud datasets. With PointNet++, our method achieves an accuracy gain of 2.6 (MN40) and ScanObjectNN, respectively. In addition to generalization performance, SageMix improves robustness and uncertainty calibration. Moreover, when adopting our method to various tasks including part segmentation and standard 2D image classification, our method achieves competitive performance.

READ FULL TEXT

page 17

page 18

page 19

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
06/29/2023

GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps

Data augmentation is now an essential part of the image training process...
research
10/11/2021

Point Cloud Augmentation with Weighted Local Transformations

Despite the extensive usage of point clouds in 3D vision, relatively lim...
research
08/14/2020

PointMixup: Augmentation for Point Clouds

This paper introduces data augmentation for point clouds by interpolatio...
research
10/31/2022

SAGE: Saliency-Guided Mixup with Optimal Rearrangements

Data augmentation is a key element for training accurate models by reduc...
research
03/12/2023

PointPatchMix: Point Cloud Mixing with Patch Scoring

Data augmentation is an effective regularization strategy for mitigating...
research
12/09/2022

Expeditious Saliency-guided Mix-up through Random Gradient Thresholding

Mix-up training approaches have proven to be effective in improving the ...

Please sign up or login with your details

Forgot password? Click here to reset