{"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/asymmetric-dual-self-distillation-for-3d-self","title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","arxiv_id":"2506.21724","date":"2025-06-26","proceeding":null,"authors":["Remco F. Leijenaar","Hamidreza Kasaei"],"abstract":"Learning semantically meaningful representations from unstructured 3D point clouds remains a central challenge in computer vision, especially in the absence of large-scale labeled datasets. While masked point modeling (MPM) is widely used in self-supervised 3D learning, its reconstruction-based objective can limit its ability to capture high-level semantics. We propose AsymDSD, an Asymmetric Dual Self-Distillation framework that unifies masked modeling and invariance learning through prediction in the latent space rather than the input space. AsymDSD builds on a joint embedding architecture and introduces several key design choices: an efficient asymmetric setup, disabling attention between masked queries to prevent shape leakage, multi-mask sampling, and a point cloud adaptation of multi-crop. AsymDSD achieves state-of-the-art results on ScanObjectNN (90.53%) and further improves to 93.72% when pretrained on 930k shapes, surpassing prior methods.","url_abs":"https://arxiv.org/abs/2506.21724v1","url_pdf":"https://arxiv.org/pdf/2506.21724v1.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":"asymmetric-dual-self-distillation-for-3d-self","repo_url":"https://github.com/RFLeijenaar/AsymDSD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"AsymDSD-B* (no voting)","rank_in_archive_order":8,"of":111,"metrics":{"Overall Accuracy":"94.7"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"AsymDSD-B* (no voting)","rank_in_archive_order":6,"of":77,"metrics":{"OBJ-BG (OA)":"96.73","OBJ-ONLY (OA)":"94.32","Overall Accuracy":"93.72"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"AsymDSD-S (no voting)","rank_in_archive_order":15,"of":77,"metrics":{"OBJ-BG (OA)":"94.32","OBJ-ONLY (OA)":"91.91","Overall Accuracy":"90.53"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}