{"url":"/sota/graph-matching-on-willow-object-class","task":{"name":"Graph Matching","url":"/task/graph-matching","note":null},"dataset":{"name":"Willow Object Class","url":null},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":"**Graph Matching** is the problem of finding correspondences between two sets of vertices while preserving complex relational information among them. Since the graph structure has a strong capacity to represent objects and robustness to severe deformation and outliers, it is frequently adopted to formulate various correspondence problems in the field of computer vision. Theoretically, the Graph Matching problem can be solved by exhaustively searching the entire solution space. However, this approach is infeasible in practice because the solution space expands exponentially as the size of input data increases. For that reason, previous studies have attempted to solve the problem by using various approximation techniques.\n\n\n<span class=\"description-source\">Source: [Consistent Multiple Graph Matching with Multi-layer Random Walks Synchronization ](https://arxiv.org/abs/1712.02575)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["matching accuracy","F1 score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"matching accuracy":"higher","F1 score":"higher"}},"counts":{"rows":23,"rows_with_code":19,"rows_with_paper_page":23,"rows_dated":23,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"COMMON","metrics":{"matching accuracy":"0.9910"},"uses_additional_data":false,"paper_date":"2022-12-08","paper":"/paper/graph-matching-with-bi-level-noisy","paper_url":"https://arxiv.org/abs/2212.04085v3","paper_title":"Graph Matching with Bi-level Noisy Correspondence","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":2,"model":"GANN-MGM","metrics":{"matching accuracy":"0.9906"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/graduated-assignment-for-joint-multi-graph","paper_url":"http://proceedings.neurips.cc/paper/2020/hash/e6384711491713d29bc63fc5eeb5ba4f-Abstract.html","paper_title":"Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"URL","metrics":{"matching accuracy":"0.989"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/universe-points-representation-learning-for","paper_url":"https://arxiv.org/abs/2212.00780v2","paper_title":"Universe Points Representation Learning for Partial Multi-Graph Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"CREAM","metrics":{"matching accuracy":"0.988"},"uses_additional_data":false,"paper_date":"2024-03-25","paper":"/paper/cross-modal-retrieval-with-noisy","paper_url":"https://ieeexplore.ieee.org/document/10477322","paper_title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","code":"https://github.com/XLearning-SCU/2024-TIP-CREAM","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Direct-MGM","metrics":{"matching accuracy":"0.987"},"uses_additional_data":false,"paper_date":"2022-05-03","paper":"/paper/learning-constrained-structured-spaces-with","paper_url":"https://proceedings.mlr.press/v206/indelman23a.html","paper_title":"Learning Constrained Structured Spaces with Application to Multi-Graph Matching","code":"https://github.com/HeddaCohenIndelman/Learning-Constrained-Structured-Spaces-with-Application-to-Multi-Graph-Matching","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GMT-BBGM","metrics":{"matching accuracy":"0.9813"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/gmtr-graph-matching-transformers","paper_url":"https://arxiv.org/abs/2311.08141v2","paper_title":"GMTR: Graph Matching Transformers","code":"https://github.com/jp-guo/gm-transformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Direct-2HGM","metrics":{"matching accuracy":"0.981"},"uses_additional_data":false,"paper_date":"2022-05-03","paper":"/paper/learning-constrained-structured-spaces-with","paper_url":"https://proceedings.mlr.press/v206/indelman23a.html","paper_title":"Learning Constrained Structured Spaces with Application to Multi-Graph Matching","code":"https://github.com/HeddaCohenIndelman/Learning-Constrained-Structured-Spaces-with-Application-to-Multi-Graph-Matching","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"qc-DGM2","metrics":{"matching accuracy":"0.977"},"uses_additional_data":false,"paper_date":"2021-03-11","paper":"/paper/deep-graph-matching-under-quadratic","paper_url":"https://arxiv.org/abs/2103.06643v2","paper_title":"Deep Graph Matching under Quadratic Constraint","code":"https://github.com/Zerg-Overmind/QC-DGM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":9,"model":"NGM-v2","metrics":{"matching accuracy":"0.9754"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/neural-graph-matching-network-learning","paper_url":"https://arxiv.org/abs/1911.11308v3","paper_title":"Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"BBGM","metrics":{"matching accuracy":"0.9718"},"uses_additional_data":false,"paper_date":"2020-03-25","paper":"/paper/deep-graph-matching-via-blackbox","paper_url":"https://arxiv.org/abs/2003.11657v2","paper_title":"Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"GCAN","metrics":{"matching accuracy":"0.9700"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/graph-context-attention-networks-for-size","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Jiang_Graph-Context_Attention_Networks_for_Size-Varied_Deep_Graph_Matching_CVPR_2022_paper.html","paper_title":"Graph-Context Attention Networks for Size-Varied Deep Graph Matching","code":"https://github.com/zhehengjiang/gcan","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"HNN-HM","metrics":{"matching accuracy":"0.968"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/hypergraph-neural-networks-for-hypergraph","paper_url":"http://openaccess.thecvf.com//content/ICCV2021/html/Liao_Hypergraph_Neural_Networks_for_Hypergraph_Matching_ICCV_2021_paper.html","paper_title":"Hypergraph Neural Networks for Hypergraph Matching","code":"https://github.com/xwliao/hnn-hm","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"GAMnet","metrics":{"matching accuracy":"0.9662"},"uses_additional_data":false,"paper_date":"2021-10-17","paper":"/paper/gamnet-robust-feature-matching-via-graph","paper_url":"https://dl.acm.org/doi/abs/10.1145/3474085.3475669","paper_title":"GAMnet: Robust Feature Matching via Graph Adversarial-Matching Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"EAGM","metrics":{"matching accuracy":"0.965"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/adaptive-edge-attention-for-graph-matching","paper_url":"https://www.ijcai.org/proceedings/2021/134","paper_title":"Adaptive Edge Attention for Graph Matching with Outliers","code":"https://github.com/bestwei/eagm","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"qc-DGM1","metrics":{"matching accuracy":"0.960"},"uses_additional_data":false,"paper_date":"2021-03-11","paper":"/paper/deep-graph-matching-under-quadratic","paper_url":"https://arxiv.org/abs/2103.06643v2","paper_title":"Deep Graph Matching under Quadratic Constraint","code":"https://github.com/Zerg-Overmind/QC-DGM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":16,"model":"GLMNet","metrics":{"matching accuracy":"0.924"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/glmnet-graph-learning-matching-networks-for","paper_url":"https://arxiv.org/abs/1911.07681v1","paper_title":"GLMNet: Graph Learning-Matching Networks for Feature Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"IPCA-GM","metrics":{"matching accuracy":"0.9006"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/combinatorial-learning-of-robust-deep-graph","paper_url":"https://ieeexplore.ieee.org/abstract/document/9128045","paper_title":"Combinatorial Learning of Robust Deep Graph Matching: an Embedding based Approach.","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"NGM","metrics":{"matching accuracy":"0.8530"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/neural-graph-matching-network-learning","paper_url":"https://arxiv.org/abs/1911.11308v3","paper_title":"Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"GMN","metrics":{"matching accuracy":"0.7934"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/deep-learning-of-graph-matching","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Zanfir_Deep_Learning_of_CVPR_2018_paper.html","paper_title":"Deep Learning of Graph Matching","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"GCAN-AFAT-I","metrics":{"F1 score":"0.837"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/deep-learning-of-partial-graph-matching-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wang_Deep_Learning_of_Partial_Graph_Matching_via_Differentiable_Top-K_CVPR_2023_paper.html","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"NGMv2-AFAT-I","metrics":{"F1 score":"0.831"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/deep-learning-of-partial-graph-matching-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wang_Deep_Learning_of_Partial_Graph_Matching_via_Differentiable_Top-K_CVPR_2023_paper.html","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"GCAN-AFAT-U","metrics":{"F1 score":"0.823"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/deep-learning-of-partial-graph-matching-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wang_Deep_Learning_of_Partial_Graph_Matching_via_Differentiable_Top-K_CVPR_2023_paper.html","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"NGMv2-AFAT-U","metrics":{"F1 score":"0.817"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/deep-learning-of-partial-graph-matching-via","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Wang_Deep_Learning_of_Partial_Graph_Matching_via_Differentiable_Top-K_CVPR_2023_paper.html","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","code":"https://github.com/Thinklab-SJTU/ThinkMatch","n_code_links":1,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":14,"n_unverified":6,"n_samples":20,"n_pointer_only_licence":12,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":16,"n_unverified":6,"n_samples":22,"n_pointer_only_licence":14,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}