# Stage-wise Adaptive Label Distribution for Facial Age Estimation

arXiv: https://arxiv.org/abs/2509.00450 · HTML: https://mlsanity.com/paper/2509.00450/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 38 references that are in the map.
- First posted on arXiv 30 Aug 2025.

## Builds on (most cited first, 14 of 14)

- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Rank consistent ordinal regression for neural networks with application to age estimation](https://mlsanity.com/paper/1901.07884/) (2019)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [An All-In-One Convolutional Neural Network for Face Analysis](https://mlsanity.com/paper/1611.00851/) (2016)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation](https://mlsanity.com/paper/1904.03358/) (2019)
- [Deep Regression Forests for Age Estimation](https://mlsanity.com/paper/1712.07195/) (2017)
- [C3AE: Exploring the Limits of Compact Model for Age Estimation](https://mlsanity.com/paper/1904.05059/) (2019)
- [Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression](https://mlsanity.com/paper/2204.00309/) (2022)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Deep Ordinal Regression with Label Diversity](https://mlsanity.com/paper/2006.15864/) (2020)
- [Deep Differentiable Random Forests for Age Estimation](https://mlsanity.com/paper/1907.10665/) (2019)
- [MetaAge: Meta-Learning Personalized Age Estimators](https://mlsanity.com/paper/2207.05288/) (2022)

## Built on by (most cited first, 1 of 1)

- [Facial Age Estimation for Age Fraud Detection in National ID Systems](https://mlsanity.com/paper/2609.05638/) (2026)

## Abstract (arXiv)

Label ambiguity poses a significant challenge in age estimation tasks. Most existing methods address this issue by modeling correlations between adjacent age groups through label distribution learning. However, they often overlook the varying degrees of ambiguity present across different age stages. In this paper, we propose a Stage-wise Adaptive Label Distribution Learning (SA-LDL) algorithm, which leverages the observation -- revealed through our analysis of embedding similarities between an anchor and all other ages -- that label ambiguity exhibits clear stage-wise patterns. By jointly employing stage-wise adaptive variance modeling and weighted loss function, SA-LDL effectively captures the complex and structured nature of label ambiguity, leading to more accurate and robust age estimation. Extensive experiments demonstrate that SA-LDL achieves competitive performance, with MAE of 1.74 and 2.15 on the MORPH-II and FG-NET datasets.