mlsanityData to 14 Oct 2026

DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception

arXiv 2401.08687 ↗First posted 13 Jan 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Camera-only Bird's Eye View (BEV) has demonstrated great potential in environment perception in a 3D space. However, most existing studies were conducted under a supervised setup which cannot scale well while handling various new data. Unsupervised domain adaptive BEV, which effective learning from various unlabelled target data, is far under-explored. In this work, we design DA-BEV, the first domain adaptive camera-only BEV framework that addresses domain adaptive BEV challenges by exploiting the complementary nature of image-view features and BEV features. DA-BEV introduces the idea of query into the domain adaptation framework to derive useful information from image-view and BEV features. It consists of two query-based designs, namely, query-based adversarial learning (QAL) and query-based self-training (QST), which exploits image-view features or BEV features to regularize the adaptation of the other. Extensive experiments show that DA-BEV achieves superior domain adaptive BEV perception performance consistently across multiple datasets and tasks such as 3D object detection and 3D scene segmentation.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 72 of its 87 references that are in the map. First posted on arXiv 13 Jan 2024.

Builds on

72 of 87 references.

References · 72

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  4. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  5. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  6. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  8. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  9. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  10. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  11. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  12. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
38 more
  1. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  2. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  3. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  4. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  5. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  6. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 281
  7. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  8. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  9. 2020One Thousand and One Hours: Self-driving Motion Prediction Datasetcited by 240
  10. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  11. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  12. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  13. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  14. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  15. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  16. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  17. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  18. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
  19. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  20. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  21. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  22. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  23. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  24. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 142
  25. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  26. 2022Vision-Centric BEV Perception: A Surveycited by 126
  27. 2022BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigscited by 123
  28. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  29. 20183D-LaneNet: End-to-End 3D Multiple Lane Detectioncited by 107
  30. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 101
  31. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  32. 2020A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye Viewcited by 72
  33. 2020Multiview Detection with Feature Perspective Transformationcited by 71
  34. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 70
  35. 2022AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detectioncited by 70
  36. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  37. 2022MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detectioncited by 62
  38. 2020FISHING Net: Future Inference of Semantic Heatmaps In Gridscited by 55

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detectioncited by 21
  2. 2024OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detectioncited by 9
  3. 2024PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentationcited by 5
  4. 2025HierDAMap: Towards Universal Domain Adaptive BEV Mapping via Hierarchical Perspective Priorscited by 2
  5. 2025NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networkscited by 0