{"url":"/sota/unbiased-scene-graph-generation-on-visual","task":{"name":"Unbiased Scene Graph Generation","url":"/task/unbiased-scene-graph-generation","note":null},"dataset":{"name":"Visual Genome","url":"/dataset/visual-genome"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Unbiased Scene Graph Generation (Unbiased SGG) aims to predict more informative scene graphs composed of more \"tail predicates\" *(in contrast to \"head predicates\" in terms of class frequencies) by dealing with the skewed, long-tailed predicate class distribution. (Definition from Chiou et al. \"Recovering the Unbiased Scene Graphs from the Biased Ones\")","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":["ng-mR@20","mR@20","F@100"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ng-mR@20":null,"mR@20":null,"F@100":null}},"counts":{"rows":31,"rows_with_code":31,"rows_with_paper_page":31,"rows_dated":31,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"44.1","mR@20":"28.9","ng-mR@20":"36.0"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/fine-grained-scene-graph-generation-with-data","paper_url":"https://arxiv.org/abs/2203.11654v2","paper_title":"Fine-Grained Scene Graph Generation with Data Transfer","code":"https://github.com/waxnkw/ietrans-sgg.pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"DPL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"44.9","mR@20":"26.2","ng-mR@20":"31.3"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/semantic-diversity-aware-prototype-based","paper_url":"https://arxiv.org/abs/2407.15396v2","paper_title":"Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation","code":"https://github.com/jeonjaehyeong/dpl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":3,"model":"DLFE (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"37.6","mR@20":"22.1","ng-mR@20":"30.0"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DLFE (VCTree-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"36.0","mR@20":"20.8","ng-mR@20":"29.1"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"35.7","mR@20":"19.3","ng-mR@20":"25.6"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"PCPL (VCTree-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"34.6","mR@20":"18.7","ng-mR@20":"25.1"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"26.0","mR@20":"17.5","ng-mR@20":"21.8"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/fine-grained-scene-graph-generation-with-data","paper_url":"https://arxiv.org/abs/2203.11654v2","paper_title":"Fine-Grained Scene Graph Generation with Data Transfer","code":"https://github.com/waxnkw/ietrans-sgg.pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"DLFE (VCTree-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"mR@20":"15.8","ng-mR@20":"21.6"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"TDE (VCTree-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"36.9","mR@20":"19.2","ng-mR@20":"20.9"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":10,"model":"TDE (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"37.2","mR@20":"17.4","ng-mR@20":"18.7"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":11,"model":"DPL (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"25.2","mR@20":"14.1","ng-mR@20":"18.5"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/semantic-diversity-aware-prototype-based","paper_url":"https://arxiv.org/abs/2407.15396v2","paper_title":"Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation","code":"https://github.com/jeonjaehyeong/dpl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"DLFE (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"21.5","mR@20":"12.8","ng-mR@20":"17.6"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PCPL (VCTree-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"23.2","mR@20":"12.7","ng-mR@20":"17.2"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"IETrans (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"21.7","mR@20":"10.9","ng-mR@20":"13.4"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/fine-grained-scene-graph-generation-with-data","paper_url":"https://arxiv.org/abs/2203.11654v2","paper_title":"Fine-Grained Scene Graph Generation with Data Transfer","code":"https://github.com/waxnkw/ietrans-sgg.pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"18.8","mR@20":"9.9","ng-mR@20":"13.1"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"TDE (VCTree-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"18.6","mR@20":"11.2","ng-mR@20":"12.4"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":17,"model":"DLFE (VCTree-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"18.1","mR@20":"8.6","ng-mR@20":"11.8"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"DLFE (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"18.8","mR@20":"8.6","ng-mR@20":"11.7"},"uses_additional_data":false,"paper_date":"2021-07-05","paper":"/paper/recovering-the-unbiased-scene-graphs-from-the","paper_url":"https://arxiv.org/abs/2107.02112v1","paper_title":"Recovering the Unbiased Scene Graphs from the Biased Ones","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"TDE (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"F@100":"19.9","mR@20":"9.9","ng-mR@20":"10.7"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":20,"model":"DPL (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"20.2","mR@20":"9.4","ng-mR@20":"10.0"},"uses_additional_data":false,"paper_date":"2024-07-22","paper":"/paper/semantic-diversity-aware-prototype-based","paper_url":"https://arxiv.org/abs/2407.15396v2","paper_title":"Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation","code":"https://github.com/jeonjaehyeong/dpl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":21,"model":"PCPL (VCTree-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"17.8","mR@20":"8.1","ng-mR@20":"9.9"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"PCPL (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"18.0","mR@20":"8.0","ng-mR@20":"9.8"},"uses_additional_data":false,"paper_date":"2020-09-02","paper":"/paper/pcpl-predicate-correlation-perception","paper_url":"https://arxiv.org/abs/2009.00893v1","paper_title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","code":"https://github.com/coldmanck/recovering-unbiased-scene-graphs","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"TDE (VCTree-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"15.1","mR@20":"6.8","ng-mR@20":"7.8"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":24,"model":"TDE (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"F@100":"13.2","mR@20":"9.7","ng-mR@20":"7.4"},"uses_additional_data":false,"paper_date":"2020-02-27","paper":"/paper/unbiased-scene-graph-generation-from-biased","paper_url":"https://arxiv.org/abs/2002.11949v3","paper_title":"Unbiased Scene Graph Generation from Biased Training","code":"https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch","n_code_links":6,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":25,"model":"SHA-GCL (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"mR@20":"35.6"},"uses_additional_data":false,"paper_date":"2022-03-18","paper":"/paper/stacked-hybrid-attention-and-group","paper_url":"https://arxiv.org/abs/2203.09811v2","paper_title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","code":"https://github.com/dongxingning/sha-gcl-for-sgg","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":26,"model":"CogTree (VCTree-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"35.9","mR@20":"22.0"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"CogTree (MOTIFS-ResNeXt-101-FPN backbone; PredCls mode)","metrics":{"F@100":"32.4","mR@20":"20.9"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"CogTree (VCTree-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"mR@20":"15.4"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"CogTree (MOTIFS-ResNeXt-101-FPN backbone; SGCls mode)","metrics":{"mR@20":"12.1"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"CogTree (MOTIFS-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"mR@20":"7.9"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"CogTree (VCTree-ResNeXt-101-FPN backbone; SGDet mode)","metrics":{"mR@20":"7.8"},"uses_additional_data":false,"paper_date":"2020-09-16","paper":"/paper/cogtree-cognition-tree-loss-for-unbiased","paper_url":"https://arxiv.org/abs/2009.07526v2","paper_title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","code":"https://github.com/CYVincent/Scene-Graph-Transformer-CogTree","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":10,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":24,"n_unverified":22,"n_samples":46,"n_pointer_only_licence":46,"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"}}}