{"url":"/sota/facial-attribute-classification-on-bffhq","task":{"name":"Facial Attribute Classification","url":"/task/facial-attribute-classification","note":null},"dataset":{"name":"bFFHQ","url":"/dataset/bffhq"},"category":"Computer Vision","categories":["Computer Vision","Miscellaneous","Music"],"category_note":null,"description":"Facial attribute classification is the task of classifying various attributes of a facial image - e.g. whether someone has a beard, is wearing a hat, and so on.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Multi-task Learning of Cascaded CNN for Facial Attribute Classification\r\n](https://arxiv.org/pdf/1805.01290v1.pdf) )</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":["Bias-Conflicting Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Bias-Conflicting Accuracy":"higher"}},"counts":{"rows":3,"rows_with_code":2,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DebiAN","metrics":{"Bias-Conflicting Accuracy":"62.8"},"uses_additional_data":false,"paper_date":"2022-07-20","paper":"/paper/discover-and-mitigate-unknown-biases-with","paper_url":"https://arxiv.org/abs/2207.10077v2","paper_title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","code":"https://github.com/zhihengli-UR/DebiAN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":2,"model":"DCWP","metrics":{"Bias-Conflicting Accuracy":"60.35"},"uses_additional_data":false,"paper_date":"2022-10-11","paper":"/paper/efficient-debiasing-with-contrastive-weight","paper_url":"https://arxiv.org/abs/2210.05247v3","paper_title":"Training Debiased Subnetworks with Contrastive Weight Pruning","code":"https://github.com/parkgeonyeong/dcwp","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"BiaSwap","metrics":{"Bias-Conflicting Accuracy":"58.87"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/biaswap-removing-dataset-bias-with-bias","paper_url":"https://arxiv.org/abs/2108.10008v1","paper_title":"BiaSwap: Removing dataset bias with bias-tailored swapping augmentation","code":null,"n_code_links":0,"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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":9,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":9,"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"}}}