PointAugment

2000년 도입 · 논문 1편에서 사용

PointAugment is a an auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods for 2D images, PointAugment is sample-aware and takes an adversarial learning strategy to jointly optimize an augmentor network and a classifier network, such that the augmentor can learn to produce augmented samples that best fit the classifier.

출처: PointAugment: an Auto-Augmentation Framework for Point Cloud Classification

소개 논문: PointAugment: an Auto-Augmentation Framework for Point Cloud Classification