# Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

arXiv: https://arxiv.org/abs/2303.05886 · HTML: https://mlsanity.com/paper/2303.05886/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Builds on (most cited first, 30 of 32)

- [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)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [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)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Frustum PointNets for 3D Object Detection from RGB-D Data](https://mlsanity.com/paper/1711.08488/) (2017)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://mlsanity.com/paper/1907.03670/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [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)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [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)
- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Multi-Anchor Active Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2108.08012/) (2021)

## Built on by (most cited first, 22 of 22)

- [Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts](https://mlsanity.com/paper/2312.02567/) (2023)
- [AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset](https://mlsanity.com/paper/2306.00612/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Perspective-Invariant 3D Object Detection](https://mlsanity.com/paper/2507.17665/) (2025)
- [Merging Vision Transformers from Different Tasks and Domains](https://mlsanity.com/paper/2312.16240/) (2023)
- [The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration](https://mlsanity.com/paper/2401.16634/) (2024)
- [ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2402.03235/) (2024)
- [ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation](https://mlsanity.com/paper/2309.05527/) (2023)
- [UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps](https://mlsanity.com/paper/2403.17633/) (2024)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [Towards Generalizable Multi-Camera 3D Object Detection via Perspective Debiasing](https://mlsanity.com/paper/2310.11346/) (2023)
- [SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations](https://mlsanity.com/paper/2309.10527/) (2023)
- [Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detection](https://mlsanity.com/paper/2407.04061/) (2024)
- [Weakly Supervised Test-Time Domain Adaptation for Object Detection](https://mlsanity.com/paper/2407.05607/) (2024)
- [CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation](https://mlsanity.com/paper/2503.09878/) (2025)
- [Single-Rollout Hidden-State Dynamics for Training-Free RLVR Data Selection](https://mlsanity.com/paper/2605.28631/) (2026)
- [Multi-view Vision-Prompt Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?](https://mlsanity.com/paper/2304.10224/) (2023)
- [CornerPoint3D: Look at the Nearest Corner Instead of the Center](https://mlsanity.com/paper/2504.02464/) (2025)
- [HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection](https://mlsanity.com/paper/2505.00507/) (2025)
- [Domain Adaptation for Different Sensor Configurations in 3D Object Detection](https://mlsanity.com/paper/2509.04711/) (2025)
- [Federated Active Learning Under Extreme Non-IID and Global Class Imbalance](https://mlsanity.com/paper/2603.10341/) (2026)
- [Autonomous Driving Research Requires a Community-Driven Data Paradigm](https://mlsanity.com/paper/2610.08825/) (2026)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently. Though preliminary progress has been made, the performance gap between the UDA-based 3D model and the supervised one trained with fully annotated target domain is still large. This motivates us to consider selecting partial-yet-important target data and labeling them at a minimum cost, to achieve a good trade-off between high performance and low annotation cost. To this end, we propose a Bi-domain active learning approach, namely Bi3D, to solve the cross-domain 3D object detection task. The Bi3D first develops a domainness-aware source sampling strategy, which identifies target-domain-like samples from the source domain to avoid the model being interfered by irrelevant source data. Then a diversity-based target sampling strategy is developed, which selects the most informative subset of target domain to improve the model adaptability to the target domain using as little annotation budget as possible. Experiments are conducted on typical cross-domain adaptation scenarios including cross-LiDAR-beam, cross-country, and cross-sensor, where Bi3D achieves a promising target-domain detection accuracy (89.63% on KITTI) compared with UDAbased work (84.29%), even surpassing the detector trained on the full set of the labeled target domain (88.98%). Our code is available at: https://github.com/PJLabADG/3DTrans.