{"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/less-is-more-reducing-task-and-model","title":"Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation","arxiv_id":"2303.11203","date":"2023-03-20","proceeding":"CVPR 2023 1","authors":["Li Li","Hubert P. H. Shum","Toby P. Breckon"],"abstract":"Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving. Existing work very often employs relatively large segmentation backbone networks to improve segmentation accuracy, at the expense of computational costs. In addition, many use uniform sampling to reduce ground truth data requirements for learning needed, often resulting in sub-optimal performance. To address these issues, we propose a new pipeline that employs a smaller architecture, requiring fewer ground-truth annotations to achieve superior segmentation accuracy compared to contemporary approaches. This is facilitated via a novel Sparse Depthwise Separable Convolution module that significantly reduces the network parameter count while retaining overall task performance. To effectively sub-sample our training data, we propose a new Spatio-Temporal Redundant Frame Downsampling (ST-RFD) method that leverages knowledge of sensor motion within the environment to extract a more diverse subset of training data frame samples. To leverage the use of limited annotated data samples, we further propose a soft pseudo-label method informed by LiDAR reflectivity. Our method outperforms contemporary semi-supervised work in terms of mIoU, using less labeled data, on the SemanticKITTI (59.5@5%) and ScribbleKITTI (58.1@5%) benchmark datasets, based on a 2.3x reduction in model parameters and 641x fewer multiply-add operations whilst also demonstrating significant performance improvement on limited training data (i.e., Less is More).","url_abs":"https://arxiv.org/abs/2303.11203v2","url_pdf":"https://arxiv.org/pdf/2303.11203v2.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":"less-is-more-reducing-task-and-model","repo_url":"https://github.com/l1997i/lim3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-scribblekitti","task":"3D Semantic Segmentation","dataset":"ScribbleKITTI","model":"LiM3D","rank_in_archive_order":5,"of":6,"metrics":{"mIoU-1%":"57"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-scribblekitti","task":"3D Semantic Segmentation","dataset":"ScribbleKITTI","model":"LiM3D+SDSC","rank_in_archive_order":6,"of":6,"metrics":{"mIoU-1%":"55.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"LiM3D","rank_in_archive_order":44,"of":45,"metrics":{"mIoU-1%":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"LiM3D+SDSC","rank_in_archive_order":45,"of":45,"metrics":{"mIoU-1%":"57.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.11203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11203"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/l1997i/lim3d","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6aa3b5f3cfdca71a","entry":"build_class_wise_memory_bank","repo":"l1997i/lim3d","repo_kind":"official","path":"utils/contra_memobank_loss.py","file_url":"https://github.com/l1997i/lim3d/blob/HEAD/utils/contra_memobank_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6aa3b5f3cfdca71a"}},{"code_sha256_prefix":"c398cef55a293907","entry":"compute_iou","repo":"l1997i/lim3d","repo_kind":"official","path":"utils/evaluation.py","file_url":"https://github.com/l1997i/lim3d/blob/HEAD/utils/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c398cef55a293907"}},{"code_sha256_prefix":"9f859fb1a07bac85","entry":"get_criterion","repo":"l1997i/lim3d","repo_kind":"official","path":"utils/contra_memobank_loss.py","file_url":"https://github.com/l1997i/lim3d/blob/HEAD/utils/contra_memobank_loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f859fb1a07bac85"}},{"code_sha256_prefix":"ad160d9d4e7a9420","entry":"load_dist","repo":"l1997i/lim3d","repo_kind":"official","path":"crb.py","file_url":"https://github.com/l1997i/lim3d/blob/HEAD/crb.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad160d9d4e7a9420"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}