mlsanityData to 7 Oct 2026

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

arXiv 2103.05346 ↗First posted 9 Mar 2021cs.CV cs.LGcited by 158

Not on the map. Why?

Abstract (arXiv)

We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strategy for mitigating the negative effects of source domain bias. Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation. These specific designs for 3D object detection enable the detector to be trained with consistent and high-quality pseudo labels and to avoid overfitting to the large number of easy examples in pseudo labeled data. Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark. Code will be available at https://github.com/CVMI-Lab/ST3D.

Key facts. Cited by 158 papers in the map (data through 7 Oct 2026). Builds on 45 of its 72 references that are in the map. First posted on arXiv 9 Mar 2021.

Builds on

45 of 72 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Mask R-CNNcited by 7,259
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
33 more
  1. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  2. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  3. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  4. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
  7. 2019Confidence Regularized Self-Trainingcited by 418
  8. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  9. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  10. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  11. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  12. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  13. 2019Mask Scoring R-CNNcited by 265
  14. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  15. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  16. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  17. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  18. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  19. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  20. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  21. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 136
  22. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  23. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  24. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  25. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  26. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  27. 2019YOLACT++: Better Real-time Instance Segmentationcited by 84
  28. 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75
  29. 2019An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentationcited by 48
  30. 2019Pseudo-Labeling Curriculum for Unsupervised Domain Adaptationcited by 46
  31. 2020Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptationcited by 35
  32. 2020SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detectioncited by 25
  33. 2018Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 31; 2023: 40; 2024: 35; 2025: 26; 2026: 13.

158 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  3. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  4. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  5. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  6. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  7. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  8. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  9. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  10. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  11. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  12. 2022LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detectioncited by 54
38 more
  1. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  2. 2022Learning to Detect Mobile Objects from LiDAR Scans Without Labelscited by 44
  3. 2022Domain Adaptive Object Detection for Autonomous Driving under Foggy Weathercited by 41
  4. 2023Uni3D: A Unified Baseline for Multi-dataset 3D Object Detectioncited by 39
  5. 2023Fast Neural Scene Flowcited by 39
  6. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  7. 2022Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptationcited by 33
  8. 2023Density-Insensitive Unsupervised Domain Adaption on 3D Object Detectioncited by 31
  9. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  10. 2023Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labelingcited by 28
  11. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  12. 2022CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detectioncited by 26
  13. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  14. 2024Real3D: Scaling Up Large Reconstruction Models with Real-World Imagescited by 24
  15. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  16. 2022Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Trainingcited by 22
  17. 2021Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detectioncited by 21
  18. 2023Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detectioncited by 21
  19. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  20. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  21. 2023AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Datasetcited by 21
  22. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  23. 2021Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 18
  24. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 17
  25. 2023DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perceptioncited by 17
  26. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Webcited by 16
  27. 2025Perspective-Invariant 3D Object Detectioncited by 16
  28. 2021See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptationcited by 15
  29. 2023MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalizationcited by 14
  30. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  31. 2024Backpropagation-free Network for 3D Test-time Adaptationcited by 14
  32. 2021Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 13
  33. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  34. 2023Unsupervised Adaptation from Repeated Traversals for Autonomous Drivingcited by 13
  35. 2023Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentationcited by 13
  36. 2023ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulationcited by 13
  37. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  38. 2023LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detectioncited by 12

50 most cited of 158 All 158 (JSON)