# Label-Efficient 3D Object Detection For Road-Side Units

arXiv: https://arxiv.org/abs/2404.06256 · HTML: https://mlsanity.com/paper/2404.06256/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://mlsanity.com/paper/2303.11301/) (2023)
- [Learning Distilled Collaboration Graph for Multi-Agent Perception](https://mlsanity.com/paper/2111.00643/) (2021)
- [V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving](https://mlsanity.com/paper/2202.08449/) (2022)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/2012.04355/) (2020)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://mlsanity.com/paper/2207.12655/) (2022)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving](https://mlsanity.com/paper/2309.14491/) (2023)
- [ICP-Flow: LiDAR Scene Flow Estimation with ICP](https://mlsanity.com/paper/2402.17351/) (2024)
- [Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2304.01464/) (2023)
- [Towards Unsupervised Object Detection From LiDAR Point Clouds](https://mlsanity.com/paper/2311.02007/) (2023)
- [4D Unsupervised Object Discovery](https://mlsanity.com/paper/2210.04801/) (2022)
- [MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2308.05988/) (2023)
- [Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery](https://mlsanity.com/paper/2310.19080/) (2023)
- [MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2304.02431/) (2023)
- [On Offline Evaluation of 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2308.12779/) (2023)
- [A9 Intersection Dataset: All You Need for Urban 3D Camera-LiDAR Roadside Perception](https://mlsanity.com/paper/2306.09266/) (2023)

## Built on by (most cited first, 3 of 3)

- [VoteFlow: Enforcing Local Rigidity in Self-Supervised Scene Flow](https://mlsanity.com/paper/2503.22328/) (2025)
- [LeAP: Consistent multi-domain 3D labeling using Foundation Models](https://mlsanity.com/paper/2502.03901/) (2025)
- [Learning 3D Perception from Others' Predictions](https://mlsanity.com/paper/2410.02646/) (2024)

## Abstract (arXiv)

Occlusion presents a significant challenge for safety-critical applications such as autonomous driving. Collaborative perception has recently attracted a large research interest thanks to the ability to enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU), thus minimizing the impact of occlusion. While significant advancement has been made, the data-hungry nature of these methods creates a major hurdle for their real-world deployment, particularly due to the need for annotated RSU data. Manually annotating the vast amount of RSU data required for training is prohibitively expensive, given the sheer number of intersections and the effort involved in annotating point clouds. We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery. Our paper introduces two new modules: one for object discovery based on a spatial-temporal aggregation of point clouds, and another for refinement. Furthermore, we demonstrate that fine-tuning on a small portion of annotated data allows our object discovery models to narrow the performance gap with, or even surpass, fully supervised models. Extensive experiments are carried out in simulated and real-world datasets to evaluate our method.