{"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/one-thing-one-click-self-training-for-weakly","title":"You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding","arxiv_id":"2303.14727","date":"2023-03-26","proceeding":null,"authors":["Zhengzhe Liu","Xiaojuan Qi","Chi-Wing Fu"],"abstract":"3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose ``One Thing One Click,'' meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate the per-category prototype to enhance the pseudo label quality and guide the iterative training. Besides, our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic and instance segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts. Codes and models are available at https://github.com/liuzhengzhe/One-Thing-One-Click.","url_abs":"https://arxiv.org/abs/2303.14727v2","url_pdf":"https://arxiv.org/pdf/2303.14727v2.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":"one-thing-one-click-self-training-for-weakly","repo_url":"https://github.com/liuzhengzhe/One-Thing-One-Click","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-instance-segmentation-1","task_name":"3D Instance Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"relation-network","task_name":"Relation Network"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.14727","atlas_url":"https://app.syntology.ai/?focus=2303.14727","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}