mlsanityData to 7 Oct 2026

COLA: COarse-LAbel multi-source LiDAR semantic segmentation for autonomous driving

arXiv 2311.03017 ↗First posted 6 Nov 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

LiDAR semantic segmentation for autonomous driving has been a growing field of interest in recent years. Datasets and methods have appeared and expanded very quickly, but methods have not been updated to exploit this new data availability and rely on the same classical datasets. Different ways of performing LIDAR semantic segmentation training and inference can be divided into several subfields, which include the following: domain generalization, source-to-source segmentation, and pre-training. In this work, we aim to improve results in all of these subfields with the novel approach of multi-source training. Multi-source training relies on the availability of various datasets at training time. To overcome the common obstacles in multi-source training, we introduce the coarse labels and call the newly created multi-source dataset COLA. We propose three applications of this new dataset that display systematic improvement over single-source strategies: COLA-DG for domain generalization (+10%), COLA-S2S for source-to-source segmentation (+5.3%), and COLA-PT for pre-training (+12%). We demonstrate that multi-source approaches bring systematic improvement over single-source approaches.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 55 of its 72 references that are in the map. First posted on arXiv 6 Nov 2023.

Builds on

55 of 72 references.

References · 55

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  9. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  11. 2021Domain Generalization: A Surveycited by 760
  12. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
38 more
  1. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  2. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  3. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  4. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  5. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  6. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  7. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  8. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  9. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  10. 2019Episodic Training for Domain Generalizationcited by 245
  11. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  12. 2021PandaSet: Advanced Sensor Suite Dataset for Autonomous Drivingcited by 186
  13. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  14. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  15. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  16. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  17. 2018IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environmentscited by 163
  18. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  19. 2021Simple multi-dataset detectioncited by 126
  20. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  21. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  22. 2019Generalizing to unseen domains via distribution matchingcited by 109
  23. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  24. 2020Object Detection with a Unified Label Space from Multiple Datasetscited by 65
  25. 2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
  26. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 41
  27. 2018Dynamic-structured Semantic Propagation Networkcited by 38
  28. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  29. 2022GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentationcited by 35
  30. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  31. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  32. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  33. 2018Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentationcited by 18
  34. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  35. 2021Multi-domain semantic segmentation with overlapping labelscited by 14
  36. 2023MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalizationcited by 14
  37. 2016Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentationcited by 13
  38. 2023Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentationcited by 13

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 2.

8 papers.

  1. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  2. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  3. 2025SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistencycited by 4
  4. 2025A Novel Multi-layer Task-centric and Data Quality Framework for Autonomous Drivingcited by 2
  5. 2025Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shiftcited by 2
  6. 2025ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Networkcited by 1
  7. 2026Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentationcited by 0
  8. 2026Modeling and Measuring Redundancy in Multisource Multimodal Data for Autonomous Drivingcited by 0