SSC3OD: Sparsely Supervised Collaborative 3D Object Detection from LiDAR Point Clouds

TL;DR

This paper introduces SSC3OD, a novel framework for collaborative 3D object detection from LiDAR point clouds that requires only minimal sparse labels per scene, utilizing self-supervised and pseudo-labeling techniques to improve performance.

Contribution

The paper proposes SSC3OD, a sparsely supervised collaborative 3D detection framework with Pillar-MAE and instance mining modules, reducing annotation effort while maintaining high accuracy.

Findings

Effective performance improvement on large-scale datasets

Reduces annotation effort with only one labeled object per scene

Outperforms existing methods in sparse supervision scenarios

Abstract

Collaborative 3D object detection, with its improved interaction advantage among multiple agents, has been widely explored in autonomous driving. However, existing collaborative 3D object detectors in a fully supervised paradigm heavily rely on large-scale annotated 3D bounding boxes, which is labor-intensive and time-consuming. To tackle this issue, we propose a sparsely supervised collaborative 3D object detection framework SSC3OD, which only requires each agent to randomly label one object in the scene. Specifically, this model consists of two novel components, i.e., the pillar-based masked autoencoder (Pillar-MAE) and the instance mining module. The Pillar-MAE module aims to reason over high-level semantics in a self-supervised manner, and the instance mining module generates high-quality pseudo labels for collaborative detectors online. By introducing these simple yet effective mechanisms, the proposed SSC3OD can alleviate the adverse impacts of incomplete annotations. We generate sparse labels based on collaborative perception datasets to evaluate our method. Extensive experiments on three large-scale datasets reveal that our proposed SSC3OD can effectively improve the performance of sparsely supervised collaborative 3D object detectors.