# Exploring Active 3D Object Detection from a Generalization Perspective

arXiv: https://arxiv.org/abs/2301.09249 · HTML: https://mlsanity.com/paper/2301.09249/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 88 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 30 of 46)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [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)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [3DSSD: Point-based 3D Single Stage Object Detector](https://mlsanity.com/paper/2002.10187/) (2020)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://mlsanity.com/paper/1907.10471/) (2019)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2203.11139/) (2022)
- [Batch Active Learning at Scale](https://mlsanity.com/paper/2107.14263/) (2021)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors](https://mlsanity.com/paper/1903.03838/) (2019)
- [Bayesian Batch Active Learning as Sparse Subset Approximation](https://mlsanity.com/paper/1908.02144/) (2019)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [Active Learning for Deep Detection Neural Networks](https://mlsanity.com/paper/1911.09168/) (2019)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint](https://mlsanity.com/paper/2204.07965/) (2022)
- [ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2107.11769/) (2021)

## Built on by (most cited first, 26 of 26)

- [Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling](https://mlsanity.com/paper/2307.07944/) (2023)
- [Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments](https://mlsanity.com/paper/2403.13556/) (2024)
- [ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2402.03235/) (2024)
- [ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.02877/) (2024)
- [KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection](https://mlsanity.com/paper/2307.07942/) (2023)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [Joint Out-of-Distribution Filtering and Data Discovery Active Learning](https://mlsanity.com/paper/2503.02491/) (2025)
- [Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection](https://mlsanity.com/paper/2503.16125/) (2025)
- [You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation](https://mlsanity.com/paper/2304.11762/) (2023)
- [Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models](https://mlsanity.com/paper/2405.14271/) (2024)
- [DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection](https://mlsanity.com/paper/2406.13891/) (2024)
- [ReBound: An Open-Source 3D Bounding Box Annotation Tool for Active Learning](https://mlsanity.com/paper/2303.06250/) (2023)
- [Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?](https://mlsanity.com/paper/2412.08973/) (2024)
- [Learn 3D VQA Better with Active Selection and Reannotation](https://mlsanity.com/paper/2507.04630/) (2025)
- [Advancing Prompt Learning through an External Layer](https://mlsanity.com/paper/2407.19674/) (2024)
- [IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection](https://mlsanity.com/paper/2511.19301/) (2025)
- [Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection](https://mlsanity.com/paper/2409.05425/) (2024)
- [STONE: A Submodular Optimization Framework for Active 3D Object Detection](https://mlsanity.com/paper/2410.03918/) (2024)
- [CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving](https://mlsanity.com/paper/2505.16524/) (2025)
- [Class-Distribution Guided Active Learning for 3D Occupancy Prediction in Autonomous Driving](https://mlsanity.com/paper/2603.27294/) (2026)
- [Open-CRB: Towards Open World Active Learning for 3D Object Detection](https://mlsanity.com/paper/2310.10391/) (2023)
- [TSceneJAL: Joint Active Learning of Traffic Scenes for 3D Object Detection](https://mlsanity.com/paper/2412.18870/) (2024)
- [Breaking the SSL-AL Barrier: A Synergistic Semi-Supervised Active Learning Framework for 3D Object Detection](https://mlsanity.com/paper/2501.15449/) (2025)
- [HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection](https://mlsanity.com/paper/2505.00507/) (2025)

## Abstract (arXiv)

To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance. Our empirical study, however, suggests that mainstream uncertainty-based and diversity-based active learning policies are not effective when applied in the 3D detection task, as they fail to balance the trade-off between point cloud informativeness and box-level annotation costs. To overcome this limitation, we jointly investigate three novel criteria in our framework Crb for point cloud acquisition - label conciseness, feature representativeness and geometric balance, which hierarchically filters out the point clouds of redundant 3D bounding box labels, latent features and geometric characteristics (e.g., point cloud density) from the unlabeled sample pool and greedily selects informative ones with fewer objects to annotate. Our theoretical analysis demonstrates that the proposed criteria align the marginal distributions of the selected subset and the prior distributions of the unseen test set, and minimizes the upper bound of the generalization error. To validate the effectiveness and applicability of Crb, we conduct extensive experiments on the two benchmark 3D object detection datasets of KITTI and Waymo and examine both one-stage (i.e., Second) and two-stage 3D detectors (i.e., Pv-rcnn). Experiments evidence that the proposed approach outperforms existing active learning strategies and achieves fully supervised performance requiring 1% and 8% annotations of bounding boxes and point clouds, respectively. Source code: https://github.com/Luoyadan/CRB-active-3Ddet.