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
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.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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