{"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/sqn-weakly-supervised-semantic-segmentation","title":"SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds","arxiv_id":"2104.04891","date":"2021-04-11","proceeding":null,"authors":["Qingyong Hu","Bo Yang","Guangchi Fang","Yulan Guo","Ales Leonardis","Niki Trigoni","Andrew Markham"],"abstract":"Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. The code is available at https://github.com/QingyongHu/SQN.","url_abs":"https://arxiv.org/abs/2104.04891v3","url_pdf":"https://arxiv.org/pdf/2104.04891v3.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":"sqn-weakly-supervised-semantic-segmentation","repo_url":"https://github.com/QingyongHu/SQN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sqn-weakly-supervised-semantic-segmentation","repo_url":"https://github.com/PointCloudYC/SQN_tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.04891","atlas_url":"https://app.syntology.ai/?focus=2104.04891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}