{"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/epic-ensemble-of-partial-point-clouds-for","title":"EPiC: Ensemble of Partial Point Clouds for Robust Classification","arxiv_id":"2303.11419","date":"2023-03-20","proceeding":"ICCV 2023 1","authors":["Meir Yossef Levi","Guy Gilboa"],"abstract":"Robust point cloud classification is crucial for real-world applications, as consumer-type 3D sensors often yield partial and noisy data, degraded by various artifacts. In this work we propose a general ensemble framework, based on partial point cloud sampling. Each ensemble member is exposed to only partial input data. Three sampling strategies are used jointly, two local ones, based on patches and curves, and a global one of random sampling. We demonstrate the robustness of our method to various local and global degradations. We show that our framework significantly improves the robustness of top classification netowrks by a large margin. Our experimental setting uses the recently introduced ModelNet-C database by Ren et al.[24], where we reach SOTA both on unaugmented and on augmented data. Our unaugmented mean Corruption Error (mCE) is 0.64 (current SOTA is 0.86) and 0.50 for augmented data (current SOTA is 0.57). We analyze and explain these remarkable results through diversity analysis. Our code is available at: https://github.com/yossilevii100/EPiC","url_abs":"https://arxiv.org/abs/2303.11419v2","url_pdf":"https://arxiv.org/pdf/2303.11419v2.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":"epic-ensemble-of-partial-point-clouds-for","repo_url":"https://github.com/yossilevii100/EPiC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[{"method_slug":"deep-ensembles","method_name":"Deep Ensembles"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-classification-on-pointcloud-c","task":"Point Cloud Classification","dataset":"PointCloud-C","model":"EPiC (PCT+WOLFMix)","rank_in_archive_order":5,"of":24,"metrics":{"mean Corruption Error (mCE)":"0.510"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-classification-on-pointcloud-c","task":"Point Cloud Classification","dataset":"PointCloud-C","model":"EPiC (DGCNN+WOLFMix)","rank_in_archive_order":6,"of":24,"metrics":{"mean Corruption Error (mCE)":"0.529"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-classification-on-pointcloud-c","task":"Point Cloud Classification","dataset":"PointCloud-C","model":"EPiC(GDANet+WOLFMix)","rank_in_archive_order":7,"of":24,"metrics":{"mean Corruption Error (mCE)":"0.530"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.11419","atlas_url":"https://app.syntology.ai/?focus=2303.11419","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}