# MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection

arXiv: https://arxiv.org/abs/2304.02431 · HTML: https://mlsanity.com/paper/2304.02431/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 5 Apr 2023.

## Builds on (most cited first, 26 of 26)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Train in Germany, Test in The USA: Making 3D Object Detectors Generalize](https://mlsanity.com/paper/2005.08139/) (2020)
- [Offboard 3D Object Detection from Point Cloud Sequences](https://mlsanity.com/paper/2103.05073/) (2021)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking](https://mlsanity.com/paper/2111.09621/) (2021)
- [Unsupervised Multi-source Domain Adaptation Without Access to Source Data](https://mlsanity.com/paper/2104.01845/) (2021)
- [3D-MAN: 3D Multi-frame Attention Network for Object Detection](https://mlsanity.com/paper/2103.16054/) (2021)
- [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://mlsanity.com/paper/2205.05979/) (2022)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://mlsanity.com/paper/2203.14956/) (2022)
- [Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation](https://mlsanity.com/paper/2103.04717/) (2021)
- [Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection](https://mlsanity.com/paper/2303.06880/) (2023)
- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://mlsanity.com/paper/2204.11590/) (2022)
- [Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection](https://mlsanity.com/paper/2103.14198/) (2021)
- [Multi-Source Domain Adaptation for Object Detection](https://mlsanity.com/paper/2106.15793/) (2021)
- [See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation](https://mlsanity.com/paper/2111.09450/) (2021)
- [Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2209.06407/) (2022)

## Built on by (most cited first, 12 of 12)

- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://mlsanity.com/paper/2405.01538/) (2024)
- [MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection](https://mlsanity.com/paper/2308.05988/) (2023)
- [UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps](https://mlsanity.com/paper/2403.17633/) (2024)
- [LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving](https://mlsanity.com/paper/2501.04005/) (2025)
- [Multimodal 3D Object Detection on Unseen Domains](https://mlsanity.com/paper/2404.11764/) (2024)
- [Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detection](https://mlsanity.com/paper/2307.01462/) (2023)
- [S3PT: Scene Semantics and Structure Guided Clustering to Boost Self-Supervised Pre-Training for Autonomous Driving](https://mlsanity.com/paper/2410.23085/) (2024)
- [Label-Efficient 3D Object Detection For Road-Side Units](https://mlsanity.com/paper/2404.06256/) (2024)
- [CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation](https://mlsanity.com/paper/2503.09878/) (2025)
- [MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models](https://mlsanity.com/paper/2503.13743/) (2025)
- [Automatic Image Annotation for Mapped Features Detection](https://mlsanity.com/paper/2412.10438/) (2024)
- [HiLO: High-Level Object Fusion for Autonomous Driving using Transformers](https://mlsanity.com/paper/2506.02554/) (2025)

## Abstract (arXiv)

We introduce Multi-Source 3D (MS3D), a new self-training pipeline for unsupervised domain adaptation in 3D object detection. Despite the remarkable accuracy of 3D detectors, they often overfit to specific domain biases, leading to suboptimal performance in various sensor setups and environments. Existing methods typically focus on adapting a single detector to the target domain, overlooking the fact that different detectors possess distinct expertise on different unseen domains. MS3D leverages this by combining different pre-trained detectors from multiple source domains and incorporating temporal information to produce high-quality pseudo-labels for fine-tuning. Our proposed Kernel-Density Estimation (KDE) Box Fusion method fuses box proposals from multiple domains to obtain pseudo-labels that surpass the performance of the best source domain detectors. MS3D exhibits greater robustness to domain shift and produces accurate pseudo-labels over greater distances, making it well-suited for high-to-low beam domain adaptation and vice versa. Our method achieved state-of-the-art performance on all evaluated datasets, and we demonstrate that the pre-trained detector's source dataset has minimal impact on the fine-tuned result, making MS3D suitable for real-world applications.