mlsanityData to 7 Oct 2026

The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration

arXiv 2401.16634 ↗First posted 30 Jan 2024cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Active learning strategies for 3D object detection in autonomous driving datasets may help to address challenges of data imbalance, redundancy, and high-dimensional data. We demonstrate the effectiveness of entropy querying to select informative samples, aiming to reduce annotation costs and improve model performance. We experiment using the BEVFusion model for 3D object detection on the nuScenes dataset, comparing active learning to random sampling and demonstrating that entropy querying outperforms in most cases. The method is particularly effective in reducing the performance gap between majority and minority classes. Class-specific analysis reveals efficient allocation of annotated resources for limited data budgets, emphasizing the importance of selecting diverse and informative data for model training. Our findings suggest that entropy querying is a promising strategy for selecting data that enhances model learning in resource-constrained environments.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 31 of its 64 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

31 of 64 references.

References · 31

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  5. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  6. 2023SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detectioncited by 83
  7. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  8. 2022"Curse of rarity" for autonomous vehiclescited by 62
  9. 2020Scalable Active Learning for Object Detectioncited by 58
  10. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  11. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  12. 2021LaneAF: Robust Multi-Lane Detection with Affinity Fieldscited by 41
19 more
  1. 20193D BAT: A Semi-Automatic, Web-based 3D Annotation Toolbox for Full-Surround, Multi-Modal Data Streamscited by 35
  2. 2023BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregationcited by 31
  3. 2020Trajectory Prediction in Autonomous Driving with a Lane Heading Auxiliary Losscited by 30
  4. 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 21
  5. 2020Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Frameworkcited by 19
  6. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  7. 2023Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Contextcited by 14
  8. 2021On Salience-Sensitive Sign Classification in Autonomous Vehicle Path Planning: Experimental Explorations with a Novel Datasetcited by 13
  9. 2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
  10. 2018Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generationcited by 12
  11. 2023Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluationscited by 11
  12. 2023Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learningcited by 10
  13. 2022MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generatorcited by 9
  14. 2023Navya3DSeg -- Navya 3D Semantic Segmentation Dataset & split generation for autonomous vehiclescited by 9
  15. 2023Multi-Task Consistency for Active Learningcited by 9
  16. 2020Co-training for On-board Deep Object Detectioncited by 4
  17. 2021Does Redundancy in AI Perception Systems Help to Test for Super-Human Automated Driving Performance?cited by 4
  18. 2023CHAMP: Crowdsourced, History-Based Advisory of Mapped Pedestrians for Safer Driver Assistance Systemscited by 3
  19. 2021Data-Driven Strategies for Hierarchical Predictive Control in Unknown Environmentscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 8; 2025: 9.

17 papers.

Sort:

By area:

  1. 2024Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Drivingcited by 52
  2. 2024Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Setscited by 25
  3. 2024ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detectioncited by 17
  4. 2024Language-Driven Active Learning for Diverse Open-Set 3D Object Detectioncited by 15
  5. 2024Evaluating Vision-Language Models for Zero-Shot Detection, Classification, and Association of Motorcycles, Passengers, and Helmetscited by 4
  6. 2024Driver Activity Classification Using Generalizable Representations from Vision-Language Modelscited by 3
  7. 2025Generalizable Prompt Learning of CLIP: A Brief Overviewcited by 3
  8. 2024Perception Without Vision for Trajectory Prediction: Ego Vehicle Dynamics as Scene Representation for Efficient Active Learning in Autonomous Drivingcited by 2
  9. 2024Advancing Prompt Learning through an External Layercited by 2
  10. 2025Towards Vision Zero: The TUM Traffic Accid3nD Datasetcited by 2
  11. 2025Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasetscited by 2
  12. 2025Enhancing Target-unspecific Tasks through a Features Matrixcited by 2
5 more
  1. 2025To Label or Not to Label: PALM -- A Predictive Model for Evaluating Sample Efficiency in Active Learning Modelscited by 2
  2. 2025Enhancing Highway Safety: Accident Detection on the A9 Test Stretch Using Roadside Sensorscited by 1
  3. 2025Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Datasetcited by 1
  4. 2025CAPS: Context-Aware Priority Sampling for Enhanced Imitation Learning in Autonomous Drivingcited by 0
  5. 2025HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detectioncited by 0