{"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/learning-from-spatio-temporal-correlation-for","title":"Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation","arxiv_id":"2410.06893","date":"2024-10-09","proceeding":null,"authors":["Seungho Lee","Hwijeong Lee","Hyunjung Shim"],"abstract":"We address the challenges of the semi-supervised LiDAR segmentation (SSLS) problem, particularly in low-budget scenarios. The two main issues in low-budget SSLS are the poor-quality pseudo-labels for unlabeled data, and the performance drops due to the significant imbalance between ground-truth and pseudo-labels. This imbalance leads to a vicious training cycle. To overcome these challenges, we leverage the spatio-temporal prior by recognizing the substantial overlap between temporally adjacent LiDAR scans. We propose a proximity-based label estimation, which generates highly accurate pseudo-labels for unlabeled data by utilizing semantic consistency with adjacent labeled data. Additionally, we enhance this method by progressively expanding the pseudo-labels from the nearest unlabeled scans, which helps significantly reduce errors linked to dynamic classes. Additionally, we employ a dual-branch structure to mitigate performance degradation caused by data imbalance. Experimental results demonstrate remarkable performance in low-budget settings (i.e., <= 5%) and meaningful improvements in normal budget settings (i.e., 5 - 50%). Finally, our method has achieved new state-of-the-art results on SemanticKITTI and nuScenes in semi-supervised LiDAR segmentation. With only 5% labeled data, it offers competitive results against fully-supervised counterparts. Moreover, it surpasses the performance of the previous state-of-the-art at 100% labeled data (75.2%) using only 20% of labeled data (76.0%) on nuScenes. The code is available on https://github.com/halbielee/PLE.","url_abs":"https://arxiv.org/abs/2410.06893v1","url_pdf":"https://arxiv.org/pdf/2410.06893v1.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":"learning-from-spatio-temporal-correlation-for","repo_url":"https://github.com/halbielee/ple","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-24","task":"Semi-Supervised Semantic Segmentation","dataset":"SemanticKITTI","model":"PLE (Voxel)","rank_in_archive_order":1,"of":12,"metrics":{"mIoU (0.5% Labels)":"52.2","mIoU (1% Labels)":"61.1","mIoU (10% Labels)":"63.1","mIoU (2% Labels)":"62.9","mIoU (20% Labels)":"64.1","mIoU (5% Labels)":"62.8","mIoU (50% Labels)":"64.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-24","task":"Semi-Supervised Semantic Segmentation","dataset":"SemanticKITTI","model":"LaserMix (Voxel)","rank_in_archive_order":2,"of":12,"metrics":{"mIoU (0.5% Labels)":"47.3","mIoU (2% Labels)":"59.2","mIoU (5% Labels)":"61.7"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-24","task":"Semi-Supervised Semantic Segmentation","dataset":"SemanticKITTI","model":"PLE (CENet, Range view)","rank_in_archive_order":3,"of":12,"metrics":{"mIoU (0.5% Labels)":"46.2","mIoU (1% Labels)":"51.5","mIoU (2% Labels)":"54.3","mIoU (5% Labels)":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-25","task":"Semi-Supervised Semantic Segmentation","dataset":"nuScenes","model":"PLE (Voxel)","rank_in_archive_order":1,"of":11,"metrics":{"mIoU (0.5% Labels)":"58","mIoU (1% Labels)":"62.9","mIoU (10% Labels)":"74.3","mIoU (2% Labels)":"67.2","mIoU (20% Labels)":"76","mIoU (5% Labels)":"72.8","mIoU (50% Labels)":"76.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-25","task":"Semi-Supervised Semantic Segmentation","dataset":"nuScenes","model":"LaserMix (Voxel)","rank_in_archive_order":2,"of":11,"metrics":{"mIoU (0.5% Labels)":"51.4","mIoU (2% Labels)":"63.9","mIoU (5% Labels)":"69.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}