LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationPseudo LabelUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Domain Confusion with Self Ensembling for Unsupervised Adaptation
Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There …
Domain AdaptationUnsupervised Domain AdaptationUnsupervised domain adaptation for medical imaging segmentation with self-ensembling
Recent advances in deep learning methods have come to define the state-of-the-art for many medical imaging applications, surpassing even human judgment in several tasks. Those models, however, when trained to reduce the …
Domain AdaptationMedical Image SegmentationSemantic SegmentationUnsupervised Domain AdaptationUnsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling
Histopathological images are generally considered as the golden standard for clinical diagnosis and cancer grading. Accurate segmentation of cells/nuclei from histopathological images is a critical step to obtain reliabl…
Cell SegmentationDomain AdaptationSegmentationUnsupervised Domain AdaptationSelf-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this challenging issue, many researchers give …
Data AugmentationDomain AdaptationSegmentationSemantic Segmentation+1MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaption in 3D Object Detection
Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a drastic drop of up to 70-90% in detection rate due to variations in lidar, geographical region, or weather conditions from their original …
3D Object DetectionDomain AdaptationDomain GeneralizationMulti-Source Unsupervised Domain Adaptation+3