Improving 3D Object Detection through Progressive Population Based Augmentation

Abstract

Data augmentation has been widely adopted for object detection in 3D point clouds. However, all previous related efforts have focused on manually designing specific data augmentation methods for individual architectures. In this work, we present the first attempt to automate the design of data augmentation policies for 3D object detection. We introduce the Progressive Population Based Augmentation (PPBA) algorithm, which learns to optimize augmentation strategies by narrowing down the search space and adopting the best parameters discovered in previous iterations. On the KITTI 3D detection 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 the StarNet and PointPillars detectors 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.

Accepted at ECCV 2020

References in corpus (10)

• Improved Regularization of Convolutional Neural Networks with Cutout
• AutoAugment: Learning Augmentation Policies from Data
• Smart Augmentation - Learning an Optimal Data Augmentation Strategy
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• HDNET: Exploiting HD Maps for 3D Object Detection
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
• APAC: Augmented PAttern Classification with Neural Networks
• StarNet: Targeted Computation for Object Detection in Point Clouds
• Scale MLPerf-0.6 models on Google TPU-v3 Pods

Cited by in corpus (5)

• AFDet: Anchor Free One Stage 3D Object Detection
• Pseudo-labeling for Scalable 3D Object Detection
• Does Data Augmentation Benefit from Split BatchNorms
• Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study
• A two-stage data association approach for 3D Multi-object Tracking