mlsanityData to 7 Oct 2026

DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection

arXiv 2203.09510 ↗First posted 17 Mar 2022cs.CV cs.AI cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

While numerous 3D detection works leverage the complementary relationship between RGB images and point clouds, developments in the broader framework of semi-supervised object recognition remain uninfluenced by multi-modal fusion. Current methods develop independent pipelines for 2D and 3D semi-supervised learning despite the availability of paired image and point cloud frames. Observing that the distinct characteristics of each sensor cause them to be biased towards detecting different objects, we propose DetMatch, a flexible framework for joint semi-supervised learning on 2D and 3D modalities. By identifying objects detected in both sensors, our pipeline generates a cleaner, more robust set of pseudo-labels that both demonstrates stronger performance and stymies single-modality error propagation. Further, we leverage the richer semantics of RGB images to rectify incorrect 3D class predictions and improve localization of 3D boxes. Evaluating on the challenging KITTI and Waymo datasets, we improve upon strong semi-supervised learning methods and observe higher quality pseudo-labels. Code will be released at https://github.com/Divadi/DetMatch

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 68 of its 86 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

68 of 86 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  12. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
38 more
  1. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  2. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  3. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  4. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  5. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  8. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  9. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  13. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  14. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  15. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  16. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  17. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  18. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  19. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  20. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  21. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  22. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  23. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  24. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  25. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  26. 2014Learning with Pseudo-Ensemblescited by 241
  27. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  28. 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
  29. 2021Multimodal Virtual Point 3D Detectioncited by 166
  30. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  31. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  32. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  33. 2021Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillationcited by 131
  34. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  35. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  36. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  37. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  38. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 7; 2025: 6.

20 papers.

Sort:

By area:

  1. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  2. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  3. 2023Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detectioncited by 24
  4. 2022Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learningcited by 23
  5. 2023DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detectioncited by 18
  6. 2023Doubly Robust Self-Trainingcited by 18
  7. 2023Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detectioncited by 14
  8. 2024Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detectioncited by 7
  9. 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labelscited by 7
  10. 2025SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Promptscited by 6
  11. 2022Boosting Semi-Supervised 3D Object Detection with Semi-Samplingcited by 3
  12. 2024Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?cited by 2
8 more
  1. 2024Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariancecited by 2
  2. 2024SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filtercited by 1
  3. 2025GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detectioncited by 1
  4. 2024Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detectioncited by 0
  5. 2024TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detectioncited by 0
  6. 2025Transferable Class Statistics and Multi-scale Feature Approximation for 3D Object Detectioncited by 0
  7. 2025SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learningcited by 0
  8. 2025Learning Adaptive Pseudo-Label Selection for Semi-Supervised 3D Object Detectioncited by 0