mlsanityData to 14 Oct 2026

xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

arXiv 1911.12676 ↗First posted 28 Nov 2019cs.CVcited by 129

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of annotations in a new domain. There are many multi-modal datasets, but most UDA approaches are uni-modal. In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation. This is challenging as the two input spaces are heterogeneous and can be impacted differently by domain shift. In xMUDA, modalities learn from each other through mutual mimicking, disentangled from the segmentation objective, to prevent the stronger modality from adopting false predictions from the weaker one. We evaluate on new UDA scenarios including day-to-night, country-to-country and dataset-to-dataset, leveraging recent autonomous driving datasets. xMUDA brings large improvements over uni-modal UDA on all tested scenarios, and is complementary to state-of-the-art UDA techniques. Code is available at https://github.com/valeoai/xmuda.

Key facts. Cited by 129 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 26; 2023: 36; 2024: 21; 2025: 18; 2026: 9.

129 papers.

Sort:

By area:

  1. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  2. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  3. 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
  4. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 129
  5. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  6. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 125
  7. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  8. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  9. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  10. 2022Scene Graph Generation: A Comprehensive Surveycited by 73
  11. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  12. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
38 more
  1. 2021EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentationcited by 59
  2. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  3. 2022LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detectioncited by 55
  4. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  5. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 54
  6. 2021A Survey on Deep Domain Adaptation for LiDAR Perceptioncited by 47
  7. 2021Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentationcited by 46
  8. 2023Three Pillars improving Vision Foundation Model Distillation for Lidarcited by 44
  9. 2022Multi-Modal Cross-Domain Alignment Network for Video Moment Retrievalcited by 43
  10. 2023Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackerscited by 43
  11. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  12. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  13. 2022GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentationcited by 35
  14. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  15. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 33
  16. 2023TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimationcited by 32
  17. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  18. 2024MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalitiescited by 28
  19. 2022CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detectioncited by 27
  20. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 26
  21. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  22. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 25
  23. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  24. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  25. 2021Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapterscited by 21
  26. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  27. 2022DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detectioncited by 20
  28. 2023Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentationcited by 20
  29. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  30. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  31. 2023Learning to Adapt SAM for Segmenting Cross-domain Point Cloudscited by 20
  32. 2022Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillationcited by 19
  33. 2021Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detectioncited by 18
  34. 2023LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillationcited by 18
  35. 2023MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentationcited by 17
  36. 2023Instant Domain Augmentation for LiDAR Semantic Segmentationcited by 16
  37. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  38. 2021See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptationcited by 15

50 most cited of 129 All 129 (JSON)