CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo
SegContrast paved the way for contrastive learning on outdoor point clouds. Its original formulation targeted individual scans in applications like autonomous driving and object detection. However, mobile mapping purposes such as digital twin cities and urban planning require large-scale dense datasets to capture the full complexity and diversity present in outdoor environments. In this paper, the SegContrast method is revisited and adapted to overcome its limitations associated with mobile mapping datasets, namely the scarcity of contrastive pairs and memory constraints. To overcome the scarcity of contrastive pairs, we propose the merging of heterogeneous datasets. However, this merging is not a straightforward procedure due to the variety of size and number of points in the point clouds of these datasets. Therefore, a data augmentation approach is designed to create a vast number of segments while optimizing the size of the point cloud samples to the allocated memory. This methodology, called CLOUDSPAM, guarantees the performance of the self-supervised model for both small- and large-scale mobile mapping point clouds. Overall, the results demonstrate the benefits of utilizing datasets with a wide range of densities and class diversity. CLOUDSPAM matched the state of the art on the KITTI-360 dataset, with a 63.6% mIoU, and came in second place on the Toronto-3D dataset. Finally, CLOUDSPAM achieved competitive results against its fully supervised counterpart with only 10% of labeled data.
Code (1)
Tasks
3D Semantic SegmentationAutonomous DrivingContrastive LearningData AugmentationDiversityLIDAR Semantic Segmentationobject-detectionObject DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains suc…
Contrastive Learningimage-classificationImage ClassificationImage Segmentation+3Local contrastive loss with pseudo-label based self-training for semi-supervised medical image segmentation
Supervised deep learning-based methods yield accurate results for medical image segmentation. However, they require large labeled datasets for this, and obtaining them is a laborious task that requires clinical expertise…
Image SegmentationMedical Image SegmentationPseudo LabelSegmentation+3Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level …
3D Semantic SegmentationContrastive LearningPseudo LabelSemantic SegmentationUnsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation
Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised …
Contrastive LearningDomain AdaptationUnsupervised Domain AdaptationAnnotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation
Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniqu…
Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation