mlsanityData to 7 Oct 2026

Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters

arXiv 2107.09783 ↗First posted 20 Jul 2021cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source domain) and testing (target domain) data originate from different LiDAR sensors. To overcome this shortcoming, we propose an unsupervised domain adaptation framework that leverages unlabeled target domain data for self-supervision, coupled with an unpaired mask transfer strategy to mitigate the impact of domain shifts. Furthermore, we introduce the gated adapter module with a small number of parameters into the network to account for target domain-specific information. Experiments adapting from both real-to-real and synthetic-to-real LiDAR semantic segmentation benchmarks demonstrate the significant improvement over prior arts.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 28 of its 32 references that are in the map. First posted on arXiv 20 Jul 2021.

Builds on

28 of 32 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  9. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  12. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
16 more
  1. 2017Learning multiple visual domains with residual adapterscited by 553
  2. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  3. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  4. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  5. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  6. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  7. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  8. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
  9. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  10. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  11. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  12. 2020Deep Visual Domain Adaptationcited by 91
  13. 20203D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentationcited by 58
  14. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  15. 2019Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentationcited by 29
  16. 2020Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributionscited by 17

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 8; 2024: 5; 2025: 4.

21 papers.

Sort:

  1. 2024UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weathercited by 24
  2. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  3. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  4. 2023MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentationcited by 17
  5. 2024Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 15
  6. 2023360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentationcited by 12
  7. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  8. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  9. 2025LeAP: Consistent multi-domain 3D labeling using Foundation Modelscited by 8
  10. 2023Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domainscited by 7
  11. 2023T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Cloudscited by 5
  12. 2024Filling Missing Values Matters for Range Image-Based Point Cloud Segmentationcited by 4
9 more
  1. 2024LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Trainingcited by 4
  2. 2022Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensorscited by 2
  3. 2024GERA: Geometric Embedding for Efficient Point Registration Analysiscited by 2
  4. 2025APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Cloudscited by 2
  5. 20253D Can Be Explored In 2D: Pseudo-Label Generation for LiDAR Point Clouds Using Sensor-Intensity-Based 2D Semantic Segmentationcited by 1
  6. 2022Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learningcited by 0
  7. 2022Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentationcited by 0
  8. 2022Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Trainingcited by 0
  9. 2025Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attackscited by 0