{"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-towards-efficient-few-shot-3d","title":"Less is More: Towards Efficient Few-shot 3D Semantic Segmentation via Training-free Networks","arxiv_id":"2308.12961","date":"2023-08-24","proceeding":null,"authors":["Xiangyang Zhu","Renrui Zhang","Bowei He","Ziyu Guo","Jiaming Liu","Hao Dong","Peng Gao"],"abstract":"To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their generalization performance on `unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead, but also incurs a significant domain gap on `unseen' classes. To tackle these issues, we propose an efficient Training-free Few-shot 3D Segmentation netwrok, TFS3D, and a further training-based variant, TFS3D-T. Without any learnable parameters, TFS3D extracts dense representations by trigonometric positional encodings, and achieves comparable performance to previous training-based methods. Due to the elimination of pre-training, TFS3D can alleviate the domain gap issue and save a substantial amount of time. Building upon TFS3D, TFS3D-T only requires to train a lightweight query-support transferring attention (QUEST), which enhances the interaction between the few-shot query and support data. Experiments demonstrate TFS3D-T improves previous state-of-the-art methods by +6.93% and +17.96% mIoU respectively on S3DIS and ScanNet, while reducing the training time by -90%, indicating superior effectiveness and efficiency.","url_abs":"https://arxiv.org/abs/2308.12961v1","url_pdf":"https://arxiv.org/pdf/2308.12961v1.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-towards-efficient-few-shot-3d","repo_url":"https://github.com/yangyangyang127/tfs3d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":null,"task_name":"Few-shot 3D semantic segmentation"},{"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/2308.12961","atlas_url":"https://app.syntology.ai/?focus=2308.12961","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}