{"type":"ScholarlyArticle","title":"Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learning","authors":[{"name":"Yaohua Zha","slug":"yaohua-zha","given":"Yaohua","family":"Zha","affiliation":""},{"name":"Tao Dai","slug":"tao-dai","given":"Tao","family":"Dai","affiliation":""},{"name":"Hang Guo","slug":"hang-guo","given":"Hang","family":"Guo","affiliation":""},{"name":"Yanzi Wang","slug":"yanzi-wang","given":"Yanzi","family":"Wang","affiliation":""},{"name":"Bin Chen","slug":"bin-chen","given":"Bin","family":"Chen","affiliation":""},{"name":"Ke Chen","slug":"ke-chen","given":"Ke","family":"Chen","affiliation":""},{"name":"Shu-Tao Xia","slug":"shu-tao-xia","given":"Shu-Tao","family":"Xia","affiliation":""}],"abstract":"Point clouds, as a primary representation of 3D data, can be categorized into scene domain point clouds and object domain point clouds. Point cloud self-supervised learning (SSL) has become a mainstream paradigm for learning 3D representations. However, existing point cloud SSL primarily focuses on learning domain-specific 3D representations within a single domain, neglecting the complementary nature of cross-domain knowledge, which limits the learning of 3D representations. In this paper, we propose to learn a comprehensive Point cloud Mixture-of-Domain-Experts model (Point-MoDE) via a block-to-scene pre-training strategy. Specifically, \r\nWe first propose a mixture-of-domain-expert model consisting of scene domain experts and multiple shared object domain experts. Furthermore, we propose a block-to-scene pretraining strategy, which leverages the features of point blocks in the object domain to regress their initial positions in the scene domain through object-level block mask reconstruction and scene-level block position regression. By integrating the complementary knowledge between object and scene, this strategy simultaneously facilitates the learning of both object-domain and scene-domain representations, leading to a more comprehensive 3D representation.\r\nExtensive experiments in downstream tasks demonstrate the superiority of our model.","doi":"10.24963/ijcai.2025/260","url":"https://ijcai.org/proceedings/2025/260","pdf":"https://ijcai.org/proceedings/2025/0260.pdf","markdown":"https://ijcai.org/proceedings/2025/260.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/260","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":260,"pages":{"first":2332,"last":2340},"keywords":["Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}