Papers › A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of...

A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark

10 Jul 2023arXiv:2307.04570archive 2025-07-28

Jakub Paplham, Vojtech Franc

Comparing different age estimation methods poses a challenge due to the unreliability of published results stemming from inconsistencies in the benchmarking process. Previous studies have reported continuous performance improvements over the past decade using specialized methods; however, our findings challenge these claims. This paper identifies two trivial, yet persistent issues with the currently used evaluation protocol and describes how to resolve them. We offer an extensive comparative analysis for state-of-the-art facial age estimation methods. Surprisingly, we find that the performance differences between the methods are negligible compared to the effect of other factors, such as facial alignment, facial coverage, image resolution, model architecture, or the amount of data used for pretraining. We use the gained insights to propose using FaRL as the backbone model and demonstrate its effectiveness on all public datasets. We make the source code and exact data splits public on GitHub.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

paplhjak/facial-age-estimation-benchmark officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression (arXiv:2204.00309; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Age EstimationBenchmarking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Age Estimation AFAD ResNet-50-Unimodal-Concentrated MAE 3.20 #2 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-Regression MAE 3.17 #3 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-OR-CNN MAE 3.16 #4 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-Mean-Variance MAE 3.16 #5 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-DLDL-v2 MAE 3.15 #6 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-Cross-Entropy MAE 3.14 #7 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-DLDL MAE 3.14 #8 of 10 Archive leaderboard report
Age Estimation AFAD ResNet-50-SORD MAE 3.14 #9 of 10 Archive leaderboard report
Age Estimation AFAD FaRL+MLP MAE 3.12 #10 of 10 Archive leaderboard report
Age Estimation AgeDB FaRL+MLP MAE 5.64 #2 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-OR-CNN MAE 5.78 #3 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-DLDL MAE 5.80 #4 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-DLDL-v2 MAE 5.80 #5 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-Cross-Entropy MAE 5.81 #6 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-SORD MAE 5.81 #7 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-Mean-Variance MAE 5.85 #8 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-Unimodal-Concentrated MAE 5.90 #9 of 10 Archive leaderboard report
Age Estimation AgeDB ResNet-50-Regression MAE 6.23 #10 of 10 Archive leaderboard report
Age Estimation CACD ResNet-50-Cross-Entropy MAE 3.96 #2 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-DLDL MAE 3.96 #3 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-DLDL-v2 MAE 3.96 #4 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-SORD MAE 3.96 #5 of 13 Archive leaderboard report
Age Estimation CACD FaRL+MLP MAE 3.96 #6 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-OR-CNN MAE 4.01 #7 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-Regression MAE 4.06 #8 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-Mean-Variance MAE 4.07 #9 of 13 Archive leaderboard report
Age Estimation CACD ResNet-50-Unimodal-Concentrated MAE 4.10 #10 of 13 Archive leaderboard report
Age Estimation ChaLearn 2016 FaRL+MLP MAE 3.38 #4 of 4 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-Unimodal-Concentrated MAE 2.78 #1 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-Cross-Entropy MAE 2.81 #2 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-DLDL MAE 2.81 #3 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-SORD MAE 2.81 #4 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-DLDL-v2 MAE 2.82 #5 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-OR-CNN MAE 2.83 #6 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-Mean-Variance MAE 2.83 #7 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) ResNet-50-Regression MAE 2.83 #8 of 9 Archive leaderboard report
Age Estimation MORPH Album2 (SE) FaRL+MLP MAE 3.04 #9 of 9 Archive leaderboard report
Age Estimation UTKFace FaRL+MLP MAE 3.87 #2 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-SORD MAE 4.36 #4 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-Cross-Entropy MAE 4.38 #6 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-DLDL MAE 4.39 #7 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-OR-CNN MAE 4.40 #8 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-DLDL-v2 MAE 4.42 #9 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-Mean-Variance MAE 4.42 #10 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-Unimodal-Concentrated MAE 4.47 #11 of 14 Archive leaderboard report
Age Estimation UTKFace ResNet-50-Regression MAE 4.72 #13 of 14 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.

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