Ensemble of Regressors to Handle Bias in Predicting Age from Facial Images
Bibliographic record
Abstract
Accurate age estimation from facial images is critical in domains such as healthcare, online safety, and demographic analytics. However, the under-representation of older adults in publicly available facial datasets introduces a significant bias in regression models, often leading to systematic underperformance for this age group. In this work, we address the challenge of age estimation under imbalanced age distributions by proposing an adaptive ensemble regression framework. Our method combines three complementary estimators: RankSim, which enforces local ranking consistency; Supervised Contrastive Regression (SupCR), which leverages relational structure in label space; and a baseline L1 regression model. The final prediction is obtained via a weighted combination of the individual outputs, with weights dynamically learned to reflect the reliability of each model across different age groups. We evaluate the proposed approach on three benchmark datasets: AgeDB, IMDB-Wiki, and UTKFace. Experiments show that our ensemble method consistently reduces the mean absolute error (MAE), particularly for the 65+ age group, where single-model approaches exhibit the largest performance gap. This study highlights the importance of model-level mitigation strategies for addressing digital ageism in facial analytics systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".