mlsanityData to 7 Oct 2026

Curricular Object Manipulation in LiDAR-based Object Detection

arXiv 2304.04248 ↗First posted 9 Apr 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper explores the potential of curriculum learning in LiDAR-based 3D object detection by proposing a curricular object manipulation (COM) framework. The framework embeds the curricular training strategy into both the loss design and the augmentation process. For the loss design, we propose the COMLoss to dynamically predict object-level difficulties and emphasize objects of different difficulties based on training stages. On top of the widely-used augmentation technique called GT-Aug in LiDAR detection tasks, we propose a novel COMAug strategy which first clusters objects in ground-truth database based on well-designed heuristics. Group-level difficulties rather than individual ones are then predicted and updated during training for stable results. Model performance and generalization capabilities can be improved by sampling and augmenting progressively more difficult objects into the training samples. Extensive experiments and ablation studies reveal the superior and generality of the proposed framework. The code is available at https://github.com/ZZY816/COM.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 9 Apr 2023.

Builds on

53 of 66 references.

References · 53

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  7. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  10. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  11. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  12. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
38 more
  1. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  2. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  3. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  4. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  5. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  6. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  7. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  8. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  9. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  10. 2020CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognitioncited by 320
  11. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  12. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  13. 2021Curriculum Learning: A Surveycited by 257
  14. 2021Voxel Transformer for 3D Object Detectioncited by 247
  15. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  16. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  17. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  18. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  19. 2017Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samplescited by 147
  20. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  21. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  22. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  23. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  24. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  25. 2019Fast Point R-CNNcited by 119
  26. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  27. 2022Curriculum Temperature for Knowledge Distillationcited by 110
  28. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  29. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  30. 2017Curriculum Learning and Minibatch Bucketing in Neural Machine Translationcited by 63
  31. 2019Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 59
  32. 2018An Empirical Exploration of Curriculum Learning for Neural Machine Translationcited by 58
  33. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  34. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  35. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  36. 2019Curriculum Self-Paced Learning for Cross-Domain Object Detectioncited by 39
  37. 2021To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernelscited by 39
  38. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 2; 2026: 4.

12 papers.

  1. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  2. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  3. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  4. 2024Deep Height Decoupling for Precise Vision-based 3D Occupancy Predictioncited by 16
  5. 2025DC-Scene: Data-Centric Learning for 3D Scene Understandingcited by 15
  6. 2024Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completioncited by 12
  7. 2024Small, Versatile and Mighty: A Range-View Perception Frameworkcited by 4
  8. 2024Learning 3D Perception from Others' Predictionscited by 4
  9. 2026Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learningcited by 3
  10. 2026SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Predictioncited by 0
  11. 2026Learning from Distributed Eyes: Leveraging Collaborative Perception for Automated Model Adaptationcited by 0
  12. 2026GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detectioncited by 0