mlsanityData to 14 Oct 2026

Open-CRB: Towards Open World Active Learning for 3D Object Detection

arXiv 2310.10391 ↗First posted 16 Oct 2023cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

LiDAR-based 3D object detection has recently seen significant advancements through active learning (AL), attaining satisfactory performance by training on a small fraction of strategically selected point clouds. However, in real-world deployments where streaming point clouds may include unknown or novel objects, the ability of current AL methods to capture such objects remains unexplored. This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts. To tackle this challenge, we propose a simple yet effective strategy called Open Label Conciseness (OLC), which mines novel 3D objects with minimal annotation costs. Our empirical results show that OLC successfully adapts the 3D detection model to the open world scenario with just a single round of selection. Any generic AL policy can then be integrated with the proposed OLC to efficiently address the OWAL-3D problem. Based on this, we introduce the Open-CRB framework, which seamlessly integrates OLC with our preliminary AL method, CRB, designed specifically for 3D object detection. We develop a comprehensive codebase for easy reproducing and future research, supporting 15 baseline methods (textiti.e., active learning, out-of-distribution detection and open world detection), 2 types of modern 3D detectors (textiti.e., one-stage SECOND and two-stage PV-RCNN) and 3 benchmark 3D datasets (textiti.e., KITTI, nuScenes and Waymo). Extensive experiments evidence that the proposed Open-CRB demonstrates superiority and flexibility in recognizing both novel and known classes with very limited labeling costs, compared to state-of-the-art baselines. Source code is available at urlhttps://github.com/Luoyadan/CRB-active-3Ddet/tree/Open-CRB.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 52 of its 91 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

52 of 91 references.

References · 52

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  6. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  7. 2017Deep Bayesian Active Learning with Image Datacited by 819
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2020A Survey of Deep Active Learningcited by 554
  10. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  11. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  12. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
38 more
  1. 2019Learning Loss for Active Learningcited by 336
  2. 2021Towards Open World Object Detectioncited by 297
  3. 2019Variational Adversarial Active Learningcited by 284
  4. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  5. 2021OW-DETR: Open-world Detection Transformercited by 129
  6. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  7. 2021Batch Active Learning at Scalecited by 127
  8. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  9. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  10. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 96
  11. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  12. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  13. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  14. 2021Influence Selection for Active Learningcited by 84
  15. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  16. 2021Multiple instance active learning for object detectioncited by 77
  17. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  18. 2019BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectorscited by 68
  19. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  20. 2022Active Learning by Feature Mixingcited by 63
  21. 2019Active Learning for Deep Detection Neural Networkscited by 62
  22. 2020State-Relabeling Adversarial Active Learningcited by 60
  23. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  24. 2022Entropy-based Active Learning for Object Detection with Progressive Diversity Constraintcited by 53
  25. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  26. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  27. 2020InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modelingcited by 35
  28. 2020On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regressioncited by 33
  29. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  30. 2023CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detectioncited by 28
  31. 2023Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labelingcited by 28
  32. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  33. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  34. 2015Hierarchical Subquery Evaluation for Active Learning on a Graphcited by 21
  35. 2018Lipschitz regularized Deep Neural Networks generalize and are adversarially robustcited by 19
  36. 2021Revisiting 3D Object Detection From an Egocentric Perspectivecited by 18
  37. 2022Active Learning Strategies for Weakly-supervised Object Detectioncited by 17
  38. 2018Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Weldingcited by 14

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.