{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cloudspam-contrastive-learning-on-unlabeled","title":"CLOUDSPAM: Contrastive Learning On Unlabeled Data for Segmentation and Pre-Training Using Aggregated Point Clouds and MoCo","arxiv_id":null,"date":"2024-10-26","proceeding":"Remote Sensing 2024 10","authors":["Reza Mahmoudi Kouhi","Olivier Stocker","Philippe Giguère","and Sylvie Daniel"],"abstract":"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.","url_abs":"https://www.mdpi.com/2072-4292/16/21/3984","url_pdf":"https://www.mdpi.com/2072-4292/16/21/3984/pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cloudspam-contrastive-learning-on-unlabeled","repo_url":"https://github.com/ERABL-UL/AdapSegCon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-kitti-360","task":"3D Semantic Segmentation","dataset":"KITTI-360","model":"DA-supervised","rank_in_archive_order":5,"of":8,"metrics":{"Model size":"37.9M","miou Val":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-kitti-360","task":"3D Semantic Segmentation","dataset":"KITTI-360","model":"CLOUDSPAM","rank_in_archive_order":6,"of":8,"metrics":{"Model size":"37.9M","miou Val":"63.6"},"uses_additional_data":true},{"leaderboard":"/sota/lidar-semantic-segmentation-on-paris-lille-3d","task":"LIDAR Semantic Segmentation","dataset":"Paris-Lille-3D","model":"CLOUDSPAM","rank_in_archive_order":6,"of":9,"metrics":{"mIOU":"0.738"},"uses_additional_data":true},{"leaderboard":"/sota/lidar-semantic-segmentation-on-paris-lille-3d","task":"LIDAR Semantic Segmentation","dataset":"Paris-Lille-3D","model":"DA-supervised","rank_in_archive_order":8,"of":9,"metrics":{"mIOU":"0.638"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-toronto-3d-l002","task":"Semantic Segmentation","dataset":"Toronto-3D L002","model":"CLOUDSPAM","rank_in_archive_order":4,"of":5,"metrics":{"mIoU":"71.8"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-toronto-3d-l002","task":"Semantic Segmentation","dataset":"Toronto-3D L002","model":"DA-supervised","rank_in_archive_order":5,"of":5,"metrics":{"mIoU":"69.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}