Improving 3D Object Detection through Progressive Population Based Augmentation

by   Shuyang Cheng, et al.

Data augmentation has been widely adopted for object detection in 3D point clouds. All previous efforts have focused on manually designing specific data augmentation methods for individual architectures, however no work has attempted to automate the design of data augmentation in 3D detection problems – as is common in 2D image-based computer vision. In this work, we present the first attempt to automate the design of data augmentation policies for 3D object detection. We present an algorithm, termed Progressive Population Based Augmentation (PPBA). PPBA learns to optimize augmentation strategies by narrowing down the search space and adopting the best parameters discovered in previous iterations. On the KITTI test set, PPBA improves the StarNet detector by substantial margins on the moderate difficulty category of cars, pedestrians, and cyclists, outperforming all current state-of-the-art single-stage detection models. Additional experiments on the Waymo Open Dataset indicate that PPBA continues to effectively improve 3D object detection on a 20x larger dataset compared to KITTI. The magnitude of the improvements may be comparable to advances in 3D perception architectures and the gains come without an incurred cost at inference time. In subsequent experiments, we find that PPBA may be up to 10x more data efficient than baseline 3D detection models without augmentation, highlighting that 3D detection models may achieve competitive accuracy with far fewer labeled examples.


page 1

page 2

page 3

page 4


Learning Data Augmentation Strategies for Object Detection

Data augmentation is a critical component of training deep learning mode...

Exploring 2D Data Augmentation for 3D Monocular Object Detection

Data augmentation is a key component of CNN based image recognition task...

LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations

Data augmentations are important in training high-performance 3D object ...

Scale-aware Automatic Augmentation for Object Detection

We propose Scale-aware AutoAug to learn data augmentation policies for o...

Improving Crowded Object Detection via Copy-Paste

Crowdedness caused by overlapping among similar objects is a ubiquitous ...

ADA: A Game-Theoretic Perspective on Data Augmentation for Object Detection

The use of random perturbations of ground truth data, such as random tra...

RangeAugment: Efficient Online Augmentation with Range Learning

State-of-the-art automatic augmentation methods (e.g., AutoAugment and R...

Please sign up or login with your details

Forgot password? Click here to reset