{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mivolo-multi-input-transformer-for-age-and","title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","arxiv_id":"2307.04616","date":"2023-07-10","proceeding":null,"authors":["Maksim Kuprashevich","Irina Tolstykh"],"abstract":"Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results even when the face is not visible in the image. To evaluate our proposed model, we conduct experiments on four popular benchmarks and achieve state-of-the-art performance, while demonstrating real-time processing capabilities. Additionally, we introduce a novel benchmark based on images from the Open Images Dataset. The ground truth annotations for this benchmark have been meticulously generated by human annotators, resulting in high accuracy answers due to the smart aggregation of votes. Furthermore, we compare our model's age recognition performance with human-level accuracy and demonstrate that it significantly outperforms humans across a majority of age ranges. Finally, we grant public access to our models, along with the code for validation and inference. In addition, we provide extra annotations for used datasets and introduce our new benchmark.","url_abs":"https://arxiv.org/abs/2307.04616v2","url_pdf":"https://arxiv.org/pdf/2307.04616v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mivolo-multi-input-transformer-for-age-and","repo_url":"https://github.com/wildchlamydia/mivolo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mivolo-multi-input-transformer-for-age-and","repo_url":"https://github.com/DILiS-lab/drivers-of-predictive-aleatoric-uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"tasks":[{"task_slug":"age-and-gender-classification","task_name":"Age And Gender Classification"},{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"age-and-gender-estimation","task_name":"Age and Gender Estimation"},{"task_slug":"facial-attribute-classification","task_name":"Facial Attribute Classification"},{"task_slug":"gender-prediction","task_name":"Gender Prediction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[{"slug":"lagenda","name":"LAGENDA","full_name":"Layer Age and Gender Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-and-gender-classification-on-adience-age","task":"Age And Gender Classification","dataset":"Adience Age","model":"MiVOLO-D1","rank_in_archive_order":3,"of":16,"metrics":{"Accuracy (5-fold)":"68.69"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-classification-on-adience","task":"Age And Gender Classification","dataset":"Adience Gender","model":"MiVOLO-D1","rank_in_archive_order":3,"of":10,"metrics":{"Accuracy (5-fold)":"96.51"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-agedb","task":"Age Estimation","dataset":"AgeDB","model":"MiVOLO-D1","rank_in_archive_order":1,"of":10,"metrics":{"MAE":"5.55"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-imdb-clean","task":"Age Estimation","dataset":"IMDB-Clean","model":"MiVOLO-D1","rank_in_archive_order":2,"of":4,"metrics":{"Average mean absolute error":"4.09"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-imdb-clean","task":"Age Estimation","dataset":"IMDB-Clean","model":"VOLO-D1 age&gender","rank_in_archive_order":3,"of":4,"metrics":{"Average mean absolute error":"4.22"},"uses_additional_data":false},{"leaderboard":"/sota/age-estimation-on-lagenda","task":"Age Estimation","dataset":"LAGENDA","model":"MiVOLO-D1","rank_in_archive_order":2,"of":2,"metrics":{"MAE":"3.99"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-utkface","task":"Age Estimation","dataset":"UTKFace","model":"MiVOLO-D1","rank_in_archive_order":1,"of":14,"metrics":{"MAE":"3.7"},"uses_additional_data":true},{"leaderboard":"/sota/age-estimation-on-utkface","task":"Age Estimation","dataset":"UTKFace","model":"VOLO-D1 age&gender","rank_in_archive_order":3,"of":14,"metrics":{"MAE":"4.23"},"uses_additional_data":false},{"leaderboard":"/sota/age-and-gender-estimation-on-lagenda-age","task":"Age and Gender Estimation","dataset":"LAGENDA age","model":"MiVOLO-D1","rank_in_archive_order":2,"of":2,"metrics":{"CS@5":"71.27","MAE":"3.99"},"uses_additional_data":true},{"leaderboard":"/sota/age-and-gender-estimation-on-lagenda-gender","task":"Age and Gender Estimation","dataset":"LAGENDA gender","model":"MiVOLO-D1","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"97.36"},"uses_additional_data":true},{"leaderboard":"/sota/facial-attribute-classification-on-fairface","task":"Facial Attribute Classification","dataset":"FairFace","model":"MiVOLO-D1","rank_in_archive_order":2,"of":3,"metrics":{"age-top1":"61.07","gender-top1":"95.73"},"uses_additional_data":true},{"leaderboard":"/sota/gender-prediction-on-agedb","task":"Gender Prediction","dataset":"AgeDB","model":"MiVOLO-D1","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"98.3"},"uses_additional_data":true},{"leaderboard":"/sota/gender-prediction-on-lagenda","task":"Gender Prediction","dataset":"LAGENDA","model":"MiVOLO-D1","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"97.36"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.04616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.04616"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DILiS-lab/drivers-of-predictive-aleatoric-uncertainty","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wildchlamydia/mivolo","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c90ebb04964d5db1","entry":"postprocess_age","repo":"wildchlamydia/mivolo","repo_kind":"official","path":"eval_pretrained.py","file_url":"https://github.com/wildchlamydia/mivolo/blob/HEAD/eval_pretrained.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c90ebb04964d5db1"}},{"code_sha256_prefix":"f210b8979316b2af","entry":"postprocess_gender","repo":"wildchlamydia/mivolo","repo_kind":"official","path":"eval_pretrained.py","file_url":"https://github.com/wildchlamydia/mivolo/blob/HEAD/eval_pretrained.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f210b8979316b2af"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}