mlsanityData to 7 Oct 2026

Bootstrapping Autonomous Driving Radars with Self-Supervised Learning

arXiv 2312.04519 ↗First posted 7 Dec 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

The perception of autonomous vehicles using radars has attracted increased research interest due its ability to operate in fog and bad weather. However, training radar models is hindered by the cost and difficulty of annotating large-scale radar data. To overcome this bottleneck, we propose a self-supervised learning framework to leverage the large amount of unlabeled radar data to pre-train radar-only embeddings for self-driving perception tasks. The proposed method combines radar-to-radar and radar-to-vision contrastive losses to learn a general representation from unlabeled radar heatmaps paired with their corresponding camera images. When used for downstream object detection, we demonstrate that the proposed self-supervision framework can improve the accuracy of state-of-the-art supervised baselines by 5.8% in mAP. Code is available at urlhttps://github.com/yiduohao/Radical.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 53 of its 76 references that are in the map. First posted on arXiv 7 Dec 2023.

Builds on

53 of 76 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2020End-to-End Object Detection with Transformerscited by 7,384
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  11. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  12. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
38 more
  1. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  4. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  5. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  6. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  7. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  8. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  10. 2017Look, Listen and Learncited by 452
  11. 2019Self-Supervised Learning by Cross-Modal Audio-Video Clusteringcited by 264
  12. 2017Objects that Soundcited by 254
  13. 2023A Cookbook of Self-Supervised Learningcited by 248
  14. 2016SoundNet: Learning Sound Representations from Unlabeled Videocited by 244
  15. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  16. 2020Self-Supervised Learning of Audio-Visual Objects from Videocited by 186
  17. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  18. 2022DETRs with Hybrid Matchingcited by 149
  19. 2019The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Datasetcited by 133
  20. 2020Learning Representations from Audio-Visual Spatial Alignmentcited by 95
  21. 2022Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervisioncited by 80
  22. 2021Raw High-Definition Radar for Multi-Task Learningcited by 69
  23. 2017Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learningcited by 67
  24. 2020CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotationscited by 60
  25. 2021RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Userscited by 52
  26. 2023Adaptive Rotated Convolution for Rotated Object Detectioncited by 51
  27. 2023Rank-DETR for High Quality Object Detectioncited by 49
  28. 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervisioncited by 36
  29. 2021Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignmentcited by 23
  30. 2020RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radarcited by 22
  31. 2022Pointillism: Accurate 3D bounding box estimation with multi-radarscited by 22
  32. 2022Multimodal contrastive learning for remote sensing taskscited by 18
  33. 2023Fine-grained Recognition with Learnable Semantic Data Augmentationcited by 17
  34. 2018Probably Unknown: Deep Inverse Sensor Modelling In Radarcited by 16
  35. 2020Deep Open Space Segmentation using Automotive Radarcited by 14
  36. 2022Unsupervised Learning for Human Sensing Using Radio Signalscited by 14
  37. 2021Self-Supervised Multi-Modal Alignment for Whole Body Medical Imagingcited by 6
  38. 2021Self-Supervised Radio-Visual Representation Learning for 6G Sensingcited by 6

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2025Guiding Audio Editing with Audio Language Modelcited by 11
  2. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  3. 2025RLM: A Vision-Language Model Approach for Radar Scene Understandingcited by 2
  4. 2024Leveraging Self-Supervised Instance Contrastive Learning for Radar Object Detectioncited by 1
  5. 2025Resounding Acoustic Fields with Reciprocitycited by 1
  6. 2025Random Walks in Self-supervised Learning for Triangular Meshescited by 0
  7. 2025Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Cloudscited by 0
  8. 2026CRISP: A Spatiotemporal Camera-Radar Backbone for Driving via Forecasting-Based World-Model Pretrainingcited by 0
  9. 20264D Radar Perception Algorithms for Autonomous Driving: A Reviewcited by 0