Rethinking Backbone Design for Lightweight 3D Object Detection in LiDAR

TL;DR

This paper introduces Dense Backbone, a lightweight, dense-layer-based backbone for 3D LiDAR object detection that reduces computational costs while maintaining detection accuracy, and demonstrates its effectiveness by adapting existing models like PillarNet.

Contribution

The paper presents the first dense-layer-based backbone specifically designed for 3D point cloud detection, improving efficiency without sacrificing accuracy.

Findings

29% reduction in model parameters

28% reduction in latency

Only 2% drop in detection accuracy

Abstract

Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despite achieving high detection performance, most of the approaches still rely on a VGG-based or ResNet-based backbone for feature exploration, which increases the model complexity. Lightweight backbone design is well-explored for 2D object detection, but research on 3D object detection still remains limited. In this work, we introduce Dense Backbone, a lightweight backbone that combines the benefits of high processing speed, lightweight architecture, and robust detection accuracy. We adapt multiple SoTA 3d object detectors, such as PillarNet, with our backbone and show that with our backbone, these models retain most of their detection capability at a significantly reduced computational cost. To our knowledge, this is the first dense-layer-based backbone tailored specifically for 3D object detection from point cloud data. DensePillarNet, our adaptation of PillarNet, achieves a 29% reduction in model parameters and a 28% reduction in latency with just a 2% drop in detection accuracy on the nuScenes test set. Furthermore, Dense Backbone's plug-and-play design allows straightforward integration into existing architectures, requiring no modifications to other network components.