On Automatic Data Augmentation for 3D Point Cloud Classification

TL;DR

This paper introduces a novel method for automatically learning data augmentation strategies for 3D point cloud classification using bilevel optimization, leading to improved performance and more principled augmentation.

Contribution

It proposes a bilevel optimization framework to learn data augmentation strategies for 3D point clouds, moving beyond heuristic methods.

Findings

Achieves competitive accuracy on standard point cloud classification tasks.

Effectively handles pose misalignment between training and test sets.

Provides insights into the learned augmentation distribution.

Abstract

Data augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics. In this work, we instead propose to automatically learn a data augmentation strategy using bilevel optimization. An augmentor is designed in a similar fashion to a conditional generator and is optimized by minimizing a base model's loss on a validation set when the augmented input is used for training the model. This formulation provides a more principled way to learn data augmentation on 3D point clouds. We evaluate our approach on standard point cloud classification tasks and a more challenging setting with pose misalignment between training and validation/test sets. The proposed strategy achieves competitive performance on both tasks and we provide further insight into the augmentor's ability to learn the validation set distribution.