{"url":"/sota/mitigating-contextual-bias-on-fgvc-aircraft","task":{"name":"Mitigating Contextual Bias","url":"/task/mitigating-contextual-bias","note":null},"dataset":{"name":"FGVC Aircraft","url":"/dataset/fgvc-aircraft-1"},"category":null,"categories":["Adversarial","Audio","Computer Code","Computer Vision","Graphs","Medical","Methodology","Miscellaneous","Natural Language Processing","Reasoning","Time Series"],"category_note":"the archive's category list for this table covers most areas; treated as no area assigned","description":"The contextual bias split of the Aircraft dataset was constructed by Dunlap et al. [https://arxiv.org/abs/2305.16289].\r\nThe split uses two visually similar classes: Boeing-767 and Airbus-322. Each image in this split is categorized as “sky”, “grass”, or “road” depending on its background, with ambiguous examples filtered out. The bias in the dataset is introduced by training on 400 samples where Airbus aircraft are exclusively associated with road backgrounds and Boeing aircraft with grass backgrounds, although both types may appear against sky backgrounds.","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":["Top-1 Accuracy (%)","OOD Accuracy (%)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top-1 Accuracy (%)":"higher","OOD Accuracy (%)":"higher"}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CAL + SaSPA","metrics":{"OOD Accuracy (%)":"41.5","Top-1 Accuracy (%)":"73.0"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/advancing-fine-grained-classification-by","paper_url":"https://arxiv.org/abs/2406.14551v2","paper_title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","code":"https://github.com/eyalmichaeli/saspa-aug","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CAL + ALIA","metrics":{"OOD Accuracy (%)":"25.1","Top-1 Accuracy (%)":"71.8"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CAL + Real-Guidance","metrics":{"OOD Accuracy (%)":"17.7","Top-1 Accuracy (%)":"71.7"},"uses_additional_data":false,"paper_date":"2023-05-22","paper":"/paper/is-synthetic-data-from-diffusion-models-ready","paper_url":"https://arxiv.org/abs/2305.12954v1","paper_title":"Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?","code":"https://github.com/zhengli97/dm-kd","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"CAL","metrics":{"OOD Accuracy (%)":"10.2","Top-1 Accuracy (%)":"71.0"},"uses_additional_data":false,"paper_date":"2021-08-19","paper":"/paper/counterfactual-attention-learning-for-fine","paper_url":"https://arxiv.org/abs/2108.08728v2","paper_title":"Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification","code":"https://github.com/raoyongming/CAL","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":3,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":1,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":17,"n_unverified":7,"n_samples":24,"n_pointer_only_licence":1,"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"}}}