{"url":"/sota/age-and-gender-classification-on-adience-age","task":{"name":"Age And Gender Classification","url":"/task/age-and-gender-classification","note":null},"dataset":{"name":"Adience Age","url":"/dataset/adience"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Age and gender classification is a dual-task of identifying the age and gender of a person from an image or video.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks](https://arxiv.org/pdf/1809.01990v2.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":["Accuracy (5-fold)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy (5-fold)":"higher"}},"counts":{"rows":16,"rows_with_code":11,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":9},"rows":[{"rank_in_archive_order":1,"model":"ViT-hSeq","metrics":{"Accuracy (5-fold)":"84.91"},"uses_additional_data":false,"paper_date":"2024-03-19","paper":"/paper/a-hybrid-transformer-sequencer-approach-for","paper_url":"https://arxiv.org/abs/2403.12483v2","paper_title":"A Hybrid Transformer-Sequencer approach for Age and Gender classification from in-wild facial images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"MiVOLO-V2","metrics":{"Accuracy (5-fold)":"69.43"},"uses_additional_data":true,"paper_date":"2024-03-04","paper":"/paper/beyond-specialization-assessing-the-1","paper_url":"https://arxiv.org/abs/2403.02302v4","paper_title":"Beyond Specialization: Assessing the Capabilities of MLLMs in Age and Gender Estimation","code":"https://github.com/wildchlamydia/mivolo","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MiVOLO-D1","metrics":{"Accuracy (5-fold)":"68.69"},"uses_additional_data":true,"paper_date":"2023-07-10","paper":"/paper/mivolo-multi-input-transformer-for-age-and","paper_url":"https://arxiv.org/abs/2307.04616v2","paper_title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","code":"https://github.com/wildchlamydia/mivolo","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"AL-ResNets-34 + IMDB-WIKI","metrics":{"Accuracy (5-fold)":"67.47"},"uses_additional_data":true,"paper_date":"2018-05-26","paper":"/paper/fine-grained-age-estimation-in-the-wild-with","paper_url":"https://arxiv.org/abs/1805.10445v2","paper_title":"Fine-Grained Age Estimation in the wild with Attention LSTM Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"R-SAAFc2 +IMDB-WIKI","metrics":{"Accuracy (5-fold)":"67.3"},"uses_additional_data":true,"paper_date":"2017-01-01","paper":"/paper/convnets-with-smooth-adaptive-activation","paper_url":"http://proceedings.mlr.press/v54/hou17a.html","paper_title":"ConvNets with Smooth Adaptive Activation Functions for Regression","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"RoR-34 + IMDB-WIKI","metrics":{"Accuracy (5-fold)":"66.74"},"uses_additional_data":true,"paper_date":"2017-10-09","paper":"/paper/age-group-and-gender-estimation-in-the-wild","paper_url":"http://arxiv.org/abs/1710.02985v1","paper_title":"Age Group and Gender Estimation in the Wild with Deep RoR Architecture","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MWR","metrics":{"Accuracy (5-fold)":"62.6"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/moving-window-regression-a-novel-approach-to","paper_url":"https://arxiv.org/abs/2203.13122v1","paper_title":"Moving Window Regression: A Novel Approach to Ordinal Regression","code":"https://github.com/nhshin-mcl/mwr","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"UNIORD-ResNet-101 (single crop, pytorch)","metrics":{"Accuracy (5-fold)":"61"},"uses_additional_data":false,"paper_date":"2020-11-15","paper":"/paper/deep-ordinal-regression-using-optimal","paper_url":"https://arxiv.org/abs/2011.07607v2","paper_title":"Deep Ordinal Regression using Optimal Transport Loss and Unimodal Output Probabilities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"RetinaFace + ArcFace + MLP + IC + Skip connections","metrics":{"Accuracy (5-fold)":"60.86"},"uses_additional_data":true,"paper_date":"2021-08-18","paper":"/paper/generalizing-mlps-with-dropouts-batch","paper_url":"https://arxiv.org/abs/2108.08186v2","paper_title":"Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections","code":"https://github.com/tae898/age-gender","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"CPG (single crop, pytorch)","metrics":{"Accuracy (5-fold)":"57.66"},"uses_additional_data":true,"paper_date":"2019-10-15","paper":"/paper/compacting-picking-and-growing-for","paper_url":"https://arxiv.org/abs/1910.06562v3","paper_title":"Compacting, Picking and Growing for Unforgetting Continual Learning","code":"https://github.com/ivclab/CPG","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"PAENet (single crop, tensorflow)","metrics":{"Accuracy (5-fold)":"57.3"},"uses_additional_data":true,"paper_date":"2019-06-10","paper":"/paper/increasingly-packing-multiple-facial","paper_url":"https://dl.acm.org/doi/10.1145/3323873.3325053","paper_title":"Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning","code":"https://github.com/ivclab/CPG","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"MegaAge","metrics":{"Accuracy (5-fold)":"56.01"},"uses_additional_data":true,"paper_date":"2017-08-31","paper":"/paper/quantifying-facial-age-by-posterior-of-age","paper_url":"http://arxiv.org/abs/1708.09687v2","paper_title":"Quantifying Facial Age by Posterior of Age Comparisons","code":"https://github.com/zyx2012/Age_estimation_BMVC2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Levi_Hassner CNN (over-sample, caffe)","metrics":{"Accuracy (5-fold)":"50.7"},"uses_additional_data":false,"paper_date":"2015-10-26","paper":"/paper/age-and-gender-classification-using","paper_url":"https://talhassner.github.io/home/publication/2015_CVPR","paper_title":"Age and Gender Classification using Convolutional Neural Networks","code":"https://github.com/dpressel/rude-carnie","n_code_links":2,"syntology":null},{"rank_in_archive_order":14,"model":"Levi_Hassner CNN (single crop, caffe)","metrics":{"Accuracy (5-fold)":"49.5"},"uses_additional_data":false,"paper_date":"2015-10-26","paper":"/paper/age-and-gender-classification-using","paper_url":"https://talhassner.github.io/home/publication/2015_CVPR","paper_title":"Age and Gender Classification using Convolutional Neural Networks","code":"https://github.com/dpressel/rude-carnie","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"LMTCNN-2-1 (single crop, tensorflow)","metrics":{"Accuracy (5-fold)":"44.26"},"uses_additional_data":false,"paper_date":"2018-06-06","paper":"/paper/joint-estimation-of-age-and-gender-from","paper_url":"http://arxiv.org/abs/1806.02023v1","paper_title":"Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications","code":"https://github.com/ivclab/agegenderLMTCNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Levi_Hassner CNN (single crop, tensorflow)","metrics":{"Accuracy (5-fold)":"44.14"},"uses_additional_data":false,"paper_date":"2015-10-26","paper":"/paper/age-and-gender-classification-using","paper_url":"https://talhassner.github.io/home/publication/2015_CVPR","paper_title":"Age and Gender Classification using Convolutional Neural Networks","code":"https://github.com/dpressel/rude-carnie","n_code_links":2,"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":3,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":0,"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"}}}