# LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation

arXiv: https://arxiv.org/abs/2309.13523 · HTML: https://mlsanity.com/paper/2309.13523/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 24 Sep 2023.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://mlsanity.com/paper/2011.10033/) (2020)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)
- [Deep Parametric Continuous Convolutional Neural Networks](https://mlsanity.com/paper/2101.06742/) (2021)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances](https://mlsanity.com/paper/2002.09147/) (2020)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1711.10288/) (2017)
- [A Survey on Deep Domain Adaptation for LiDAR Perception](https://mlsanity.com/paper/2106.02377/) (2021)
- [Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.09744/) (2022)

## Built on by (most cited first, 14 of 14)

- [Learning to Adapt SAM for Segmenting Cross-domain Point Clouds](https://mlsanity.com/paper/2310.08820/) (2023)
- [PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding](https://mlsanity.com/paper/2411.00632/) (2024)
- [Lidar Panoptic Segmentation in an Open World](https://mlsanity.com/paper/2409.14273/) (2024)
- [Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains](https://mlsanity.com/paper/2312.12098/) (2023)
- [Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2403.18469/) (2024)
- [HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation](https://mlsanity.com/paper/2407.12387/) (2024)
- [TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models](https://mlsanity.com/paper/2403.11691/) (2024)
- [LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Training](https://mlsanity.com/paper/2410.15833/) (2024)
- [Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2511.17455/) (2025)
- [Source-Free Domain Adaptation for Geospatial Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2601.08375/) (2026)
- [RAFT -- A Domain Adaptation Framework for RGB & LiDAR Semantic Segmentation](https://mlsanity.com/paper/2505.04529/) (2025)
- [Multi-View Projection for Unsupervised Domain Adaptation in 3D Semantic Segmentation](https://mlsanity.com/paper/2505.15545/) (2025)
- [Cross-view Domain Generalization via Geometric Consistency for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2602.14525/) (2026)
- [CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentation](https://mlsanity.com/paper/2607.10087/) (2026)

## Abstract (arXiv)

We introduce LiDAR-UDA, a novel two-stage self-training-based Unsupervised Domain Adaptation (UDA) method for LiDAR segmentation. Existing self-training methods use a model trained on labeled source data to generate pseudo labels for target data and refine the predictions via fine-tuning the network on the pseudo labels. These methods suffer from domain shifts caused by different LiDAR sensor configurations in the source and target domains. We propose two techniques to reduce sensor discrepancy and improve pseudo label quality: 1) LiDAR beam subsampling, which simulates different LiDAR scanning patterns by randomly dropping beams; 2) cross-frame ensembling, which exploits temporal consistency of consecutive frames to generate more reliable pseudo labels. Our method is simple, generalizable, and does not incur any extra inference cost. We evaluate our method on several public LiDAR datasets and show that it outperforms the state-of-the-art methods by more than 3.9% mIoU on average for all scenarios. Code will be available at https://github.com/JHLee0513/LiDARUDA.