{"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/point-jepa-a-joint-embedding-predictive","title":"Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud","arxiv_id":"2404.16432","date":"2024-04-25","proceeding":null,"authors":["Ayumu Saito","Prachi Kudeshia","Jiju Poovvancheri"],"abstract":"Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in the input space, or the necessity of additional modalities. In order to address these issues, we introduce Point-JEPA, a joint embedding predictive architecture designed specifically for point cloud data. To this end, we introduce a sequencer that orders point cloud patch embeddings to efficiently compute and utilize their proximity based on the indices during target and context selection. The sequencer also allows shared computations of the patch embeddings' proximity between context and target selection, further improving the efficiency. Experimentally, our method achieves competitive results with state-of-the-art methods while avoiding the reconstruction in the input space or additional modality.","url_abs":"https://arxiv.org/abs/2404.16432v5","url_pdf":"https://arxiv.org/pdf/2404.16432v5.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":"point-jepa-a-joint-embedding-predictive","repo_url":"https://github.com/Ayumu-J-S/Point-JEPA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"3d-point-cloud-linear-classification","task_name":"3D Point Cloud Linear Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"Point-JEPA","rank_in_archive_order":62,"of":67,"metrics":{"Class Average IoU":"85.8","Instance Average IoU":"83.9 "},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Point-JEPA (voting)","rank_in_archive_order":25,"of":111,"metrics":{"Overall Accuracy":"94.1±0.1"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"Point-JEPA (no voting)","rank_in_archive_order":46,"of":111,"metrics":{"Overall Accuracy":"93.8±0.2"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"Point-JEPA","rank_in_archive_order":47,"of":77,"metrics":{"OBJ-BG (OA)":"92.9±0.4","Overall Accuracy":"86.6"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-linear-classification-on","task":"3D Point Cloud Linear Classification","dataset":"ModelNet40","model":"Point-JEPA","rank_in_archive_order":1,"of":20,"metrics":{"Overall Accuracy":"93.7±0.2"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"Point-JEPA","rank_in_archive_order":1,"of":31,"metrics":{"Overall Accuracy":"95.0","Standard Deviation":"3.6"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-4","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (20-shot)","model":"Point-JEPA","rank_in_archive_order":2,"of":31,"metrics":{"Overall Accuracy":"96.4","Standard Deviation":"2.7"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"Point-JEPA","rank_in_archive_order":5,"of":30,"metrics":{"Overall Accuracy":"97.4","Standard Deviation":"2.2"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-2","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (20-shot)","model":"Point-JEPA","rank_in_archive_order":2,"of":30,"metrics":{"Overall Accuracy":"99.2","Standard Deviation":"0.8"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.16432","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}