{"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/universe-points-representation-learning-for","title":"Universe Points Representation Learning for Partial Multi-Graph Matching","arxiv_id":"2212.00780","date":"2022-12-01","proceeding":null,"authors":["Zhakshylyk Nurlanov","Frank R. Schmidt","Florian Bernard"],"abstract":"Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this work, we study the more general partial matching problem with multi-graph cycle consistency guarantees. Building on a recent progress in deep learning on graphs, we propose a novel data-driven method (URL) for partial multi-graph matching, which uses an object-to-universe formulation and learns latent representations of abstract universe points. The proposed approach advances the state of the art in semantic keypoint matching problem, evaluated on Pascal VOC, CUB, and Willow datasets. Moreover, the set of controlled experiments on a synthetic graph matching dataset demonstrates the scalability of our method to graphs with large number of nodes and its robustness to high partiality.","url_abs":"https://arxiv.org/abs/2212.00780v2","url_pdf":"https://arxiv.org/pdf/2212.00780v2.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":[],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/graph-matching-on-cub","task":"Graph Matching","dataset":"CUB","model":"URL","rank_in_archive_order":1,"of":4,"metrics":{"F1 score":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/graph-matching-on-pascal-voc","task":"Graph Matching","dataset":"PASCAL VOC","model":"URL","rank_in_archive_order":1,"of":31,"metrics":{"F1 score":"0.717±0.005","matching accuracy":"0.818"},"uses_additional_data":false},{"leaderboard":"/sota/graph-matching-on-willow-object-class","task":"Graph Matching","dataset":"Willow Object Class","model":"URL","rank_in_archive_order":3,"of":23,"metrics":{"matching accuracy":"0.989"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}