Papers › MiVOLO: Multi-input Transformer for Age and Gender Estimation

MiVOLO: Multi-input Transformer for Age and Gender Estimation

10 Jul 2023arXiv:2307.04616archive 2025-07-28

Maksim Kuprashevich, Irina Tolstykh

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.04616")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wildchlamydia/mivolo officialmentioned in papermentioned on GitHubpytorch report
DILiS-lab/drivers-of-predictive-aleatoric-uncertainty mentioned on GitHubpytorchCC-BY-SA-4.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

2 samples harvested; 2 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from wildchlamydia/mivolo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

postprocess_age wildchlamydia/mivolo/eval_pretrained.py official repository ran · our draft was wrong Apache-2.0 (permissive) · c90ebb04964d5db1 · report
postprocess_gender wildchlamydia/mivolo/eval_pretrained.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · f210b8979316b2af · report

Tasks

Age And Gender ClassificationAge EstimationAge and Gender EstimationFacial Attribute ClassificationGender Prediction

Datasets

Introduced by this paper, per the archive.

LAGENDA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Age And Gender Classification Adience Age MiVOLO-D1 Accuracy (5-fold) 68.69 #3 of 16 Archive leaderboard report
Age And Gender Classification Adience Gender MiVOLO-D1 Accuracy (5-fold) 96.51 #3 of 10 Archive leaderboard report
Age Estimation AgeDB MiVOLO-D1 MAE 5.55 #1 of 10 Archive leaderboard report
Age Estimation IMDB-Clean MiVOLO-D1 Average mean absolute error 4.09 #2 of 4 Archive leaderboard report
Age Estimation IMDB-Clean VOLO-D1 age&gender Average mean absolute error 4.22 #3 of 4 Archive leaderboard report
Age Estimation LAGENDA MiVOLO-D1 MAE 3.99 #2 of 2 Archive leaderboard report
Age Estimation UTKFace MiVOLO-D1 MAE 3.7 #1 of 14 Archive leaderboard report
Age Estimation UTKFace VOLO-D1 age&gender MAE 4.23 #3 of 14 Archive leaderboard report
Age and Gender Estimation LAGENDA age MiVOLO-D1 CS@5 71.27 #2 of 2 Archive leaderboard report
Age and Gender Estimation LAGENDA age MiVOLO-D1 MAE 3.99 #2 of 2 Archive leaderboard report
Age and Gender Estimation LAGENDA gender MiVOLO-D1 Accuracy 97.36 #1 of 2 Archive leaderboard report
Facial Attribute Classification FairFace MiVOLO-D1 age-top1 61.07 #2 of 3 Archive leaderboard report
Facial Attribute Classification FairFace MiVOLO-D1 gender-top1 95.73 #2 of 3 Archive leaderboard report
Gender Prediction AgeDB MiVOLO-D1 Accuracy 98.3 #1 of 1 Archive leaderboard report
Gender Prediction LAGENDA MiVOLO-D1 Accuracy 97.36 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections