mlsanityData to 14 Oct 2026

STONE: A Submodular Optimization Framework for Active 3D Object Detection

arXiv 2410.03918 ↗First posted 4 Oct 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D object detection is fundamentally important for various emerging applications, including autonomous driving and robotics. A key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point cloud data. Unfortunately, labeling point cloud data is extremely challenging, as accurate 3D bounding boxes and semantic labels are required for each potential object. This paper proposes a unified active 3D object detection framework, for greatly reducing the labeling cost of training 3D object detectors. Our framework is based on a novel formulation of submodular optimization, specifically tailored to the problem of active 3D object detection. In particular, we address two fundamental challenges associated with active 3D object detection: data imbalance and the need to cover the distribution of the data, including LiDAR-based point cloud data of varying difficulty levels. Extensive experiments demonstrate that our method achieves state-of-the-art performance with high computational efficiency compared to existing active learning methods. The code is available at https://github.com/RuiyuM/STONE.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 63 references that are in the map. First posted on arXiv 4 Oct 2024.

Builds on

33 of 63 references.

References · 33

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  10. 2019Learning Loss for Active Learningcited by 336
  11. 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 147
  12. 2019Discriminative Active Learningcited by 98
21 more
  1. 2021GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learningcited by 95
  2. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  3. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  4. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 84
  5. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  6. 2019Bayesian Batch Active Learning as Sparse Subset Approximationcited by 68
  7. 2020Scalable Active Learning for Object Detectioncited by 58
  8. 2019Bayesian Generative Active Deep Learningcited by 57
  9. 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 51
  10. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  11. 2019Deep Active Learning for Efficient Training of a LiDAR 3D Object Detectorcited by 45
  12. 2022Submodularity In Machine Learning and Artificial Intelligencecited by 38
  13. 2020InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modelingcited by 35
  14. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  15. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  16. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  17. 2022AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuningcited by 22
  18. 2021Revisiting 3D Object Detection From an Egocentric Perspectivecited by 18
  19. 2019Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importancecited by 14
  20. 2023KECOR: Kernel Coding Rate Maximization for Active 3D Object Detectioncited by 13
  21. 2024Inconsistency-Based Data-Centric Active Open-Set Annotationcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detectioncited by 2