{"url":"/task/facial-attribute-classification","name":"Facial Attribute Classification","slug":"facial-attribute-classification","description_markdown":"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>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":37,"papers_with_code":18,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/facial-attribute-classification-on-lfwa","slug":"facial-attribute-classification-on-lfwa","dataset":"LFWA","dataset_url":"/dataset/lfwa","rows_in_archive":7,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"Label2Label","paper_title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","paper_url":"/paper/label2label-a-language-modeling-framework-for","paper_date":"2022-07-18","arxiv_id":"2207.08677","code_links":[{"title":"li-wanhua/label2label","url":"https://github.com/li-wanhua/label2label"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}}},{"leaderboard":"/sota/facial-attribute-classification-on-bffhq","slug":"facial-attribute-classification-on-bffhq","dataset":"bFFHQ","dataset_url":"/dataset/bffhq","rows_in_archive":3,"metrics":["Bias-Conflicting Accuracy"],"first_row_in_archive_order":{"model":"DebiAN","paper_title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","paper_url":"/paper/discover-and-mitigate-unknown-biases-with","paper_date":"2022-07-20","arxiv_id":"2207.10077","code_links":[{"title":"zhihengli-UR/DebiAN","url":"https://github.com/zhihengli-UR/DebiAN"}],"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":9}}},{"leaderboard":"/sota/facial-attribute-classification-on-fairface","slug":"facial-attribute-classification-on-fairface","dataset":"FairFace","dataset_url":"/dataset/fairface","rows_in_archive":3,"metrics":["gender-top1","race-top1","age-top1"],"first_row_in_archive_order":{"model":"MiVOLO-V2","paper_title":"Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation","paper_url":"/paper/beyond-specialization-assessing-the-1","paper_date":"2024-03-04","arxiv_id":"2403.02302","code_links":[{"title":"wildchlamydia/mivolo","url":"https://github.com/wildchlamydia/mivolo"}],"syntology":null}},{"leaderboard":"/sota/facial-attribute-classification-on-celebv-hq","slug":"facial-attribute-classification-on-celebv-hq","dataset":"CelebV-HQ","dataset_url":"/dataset/celebv-hq","rows_in_archive":1,"metrics":["AUC","Accuracy"],"first_row_in_archive_order":{"model":"MARLIN","paper_title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","paper_url":"/paper/marlin-masked-autoencoder-for-facial-video","paper_date":"2022-11-12","arxiv_id":"2211.06627","code_links":[{"title":"ControlNet/MARLIN","url":"https://github.com/ControlNet/MARLIN"}],"syntology":null}},{"leaderboard":"/sota/facial-attribute-classification-on-diveface","slug":"facial-attribute-classification-on-diveface","dataset":"DiveFace","dataset_url":"/dataset/diveface","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Neighbour Learning","paper_title":"Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups","paper_url":"/paper/deep-generative-views-to-mitigate-gender","paper_date":"2022-08-17","arxiv_id":"2208.08382","code_links":[],"syntology":null}},{"leaderboard":"/sota/facial-attribute-classification-on-morph","slug":"facial-attribute-classification-on-morph","dataset":"MORPH","dataset_url":"/dataset/morph","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Neighbour Learning","paper_title":"Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups","paper_url":"/paper/deep-generative-views-to-mitigate-gender","paper_date":"2022-08-17","arxiv_id":"2208.08382","code_links":[],"syntology":null}},{"leaderboard":"/sota/facial-attribute-classification-on-utkface","slug":"facial-attribute-classification-on-utkface","dataset":"UTKFace","dataset_url":"/dataset/utkface","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Neighbour Learning","paper_title":"Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups","paper_url":"/paper/deep-generative-views-to-mitigate-gender","paper_date":"2022-08-17","arxiv_id":"2208.08382","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/utkface","name":"UTKFace","full_name":"","num_papers_in_archive":243},{"url":"/dataset/fairface","name":"FairFace","full_name":"","num_papers_in_archive":208},{"url":"/dataset/morph","name":"MORPH","full_name":"","num_papers_in_archive":180},{"url":"/dataset/lfwa","name":"LFWA","full_name":"","num_papers_in_archive":63},{"url":"/dataset/celebv-hq","name":"CelebV-HQ","full_name":"","num_papers_in_archive":36},{"url":"/dataset/bffhq","name":"bFFHQ","full_name":"Gender-biased FFHQ dataset","num_papers_in_archive":18},{"url":"/dataset/diveface","name":"DiveFace","full_name":"","num_papers_in_archive":11},{"url":"/dataset/imdb-clean","name":"IMDB-Clean","full_name":"","num_papers_in_archive":3},{"url":"/dataset/a-view-from-somewhere-avfs","name":"A View From Somewhere (AVFS)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/laofiw-dataset","name":"LAOFIW Dataset","full_name":"Labeled Ancestral Origin Faces in the Wild","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/facial-recognition-and-modelling","name":"Facial Recognition and Modelling"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":37,"items":[{"url":"/paper/fairface-face-attribute-dataset-for-balanced","title":"FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age","date":"2019-08-14","arxiv_id":"1908.04913","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/facexformer-a-unified-transformer-for-facial","title":"FaceXFormer: A Unified Transformer for Facial Analysis","date":"2024-03-19","arxiv_id":"2403.12960","repositories_listed":2,"syntology":null},{"url":"/paper/mivolo-multi-input-transformer-for-age-and","title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","date":"2023-07-10","arxiv_id":"2307.04616","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-from-failure-training-debiased","title":"Learning from Failure: Training Debiased Classifier from Biased Classifier","date":"2020-07-06","arxiv_id":"2007.02561","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/deep-learning-face-attributes-in-the-wild","title":"Deep Learning Face Attributes in the Wild","date":"2014-11-28","arxiv_id":"1411.7766","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/fineface-fair-facial-attribute-classification","title":"FineFACE: Fair Facial Attribute Classification Leveraging Fine-grained Features","date":"2024-08-29","arxiv_id":"2408.16881","repositories_listed":1,"syntology":null},{"url":"/paper/distributionally-generative-augmentation-for","title":"Distributionally Generative Augmentation for Fair Facial Attribute Classification","date":"2024-03-11","arxiv_id":"2403.06606","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":11}},{"url":"/paper/beyond-specialization-assessing-the-1","title":"Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation","date":"2024-03-04","arxiv_id":"2403.02302","repositories_listed":1,"syntology":null},{"url":"/paper/towards-machine-unlearning-benchmarks","title":"Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems","date":"2023-11-03","arxiv_id":"2311.02240","repositories_listed":1,"syntology":null},{"url":"/paper/marlin-masked-autoencoder-for-facial-video","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","date":"2022-11-12","arxiv_id":"2211.06627","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-and-accuracy-of-celeba-attribute","title":"Consistency and Accuracy of CelebA Attribute Values","date":"2022-10-13","arxiv_id":"2210.07356","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-debiasing-with-contrastive-weight","title":"Training Debiased Subnetworks with Contrastive Weight Pruning","date":"2022-10-11","arxiv_id":"2210.05247","repositories_listed":1,"syntology":null},{"url":"/paper/discover-and-mitigate-unknown-biases-with","title":"Discover and Mitigate Unknown Biases with Debiasing Alternate Networks","date":"2022-07-20","arxiv_id":"2207.10077","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":9}},{"url":"/paper/label2label-a-language-modeling-framework-for","title":"Label2Label: A Language Modeling Framework for Multi-Attribute Learning","date":"2022-07-18","arxiv_id":"2207.08677","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/fair-contrastive-learning-for-facial","title":"Fair Contrastive Learning for Facial Attribute Classification","date":"2022-03-30","arxiv_id":"2203.16209","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/imbalanced-deep-learning-by-minority-class","title":"Imbalanced Deep Learning by Minority Class Incremental Rectification","date":"2018-04-28","arxiv_id":"1804.10851","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-information-factorization","title":"Adversarial Information Factorization","date":"2017-11-14","arxiv_id":"1711.05175","repositories_listed":1,"syntology":null},{"url":"/paper/panda-pose-aligned-networks-for-deep","title":"PANDA: Pose Aligned Networks for Deep Attribute Modeling","date":"2013-11-21","arxiv_id":"1311.5591","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}