# General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone

arXiv: https://arxiv.org/abs/2307.10129 · HTML: https://mlsanity.com/paper/2307.10129/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 65 references that are in the map.
- First posted on arXiv 19 Jul 2023.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment](https://mlsanity.com/paper/2305.11733/) (2023)
- [Self Supervision to Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.04075/) (2021)
- [Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2203.15359/) (2022)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [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)
- [Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.06094/) (2021)
- [PML: Progressive Margin Loss for Long-tailed Age Classification](https://mlsanity.com/paper/2103.02140/) (2021)
- [Fine-Grained Age Estimation in the wild with Attention LSTM Networks](https://mlsanity.com/paper/1805.10445/) (2018)
- [NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.16709/) (2023)
- [Self-Paced Deep Regression Forests with Consideration on Underrepresented Examples](https://mlsanity.com/paper/2004.01459/) (2020)
- [Soft-ranking Label Encoding for Robust Facial Age Estimation](https://mlsanity.com/paper/1906.03625/) (2019)
- [Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation](https://mlsanity.com/paper/2007.01771/) (2020)
- [LAE : Long-tailed Age Estimation](https://mlsanity.com/paper/2110.12741/) (2021)

## Built on by (most cited first, 2 of 2)

- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation](https://mlsanity.com/paper/2502.05423/) (2025)

## Abstract (arXiv)

Facial age estimation has received a lot of attention for its diverse application scenarios. Most existing studies treat each sample equally and aim to reduce the average estimation error for the entire dataset, which can be summarized as General Age Estimation. However, due to the long-tailed distribution prevalent in the dataset, treating all samples equally will inevitably bias the model toward the head classes (usually the adult with a majority of samples). Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation. However, Long-tailed Age Estimation usually faces a performance trade-off, i.e., achieving improvement in tail classes by sacrificing the head classes. In this paper, our goal is to design a unified framework to perform well on both tasks, killing two birds with one stone. To this end, we propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively. Compared to the previous best method, MAE dropped by up to 34%, which is an unprecedented improvement, and for the first time, MAE is close to 1 year old. Extensive experiments on other age benchmark datasets, including CACD, MIVIA, and Chalearn LAP 2015, also indicate that GLAE outperforms the state-of-the-art approaches significantly.