# Overcoming Occlusions in the Wild: A Multi-Task Age Head Approach to Age Estimation

arXiv: https://arxiv.org/abs/2506.13445 · HTML: https://mlsanity.com/paper/2506.13445/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Rank consistent ordinal regression for neural networks with application to age estimation](https://mlsanity.com/paper/1901.07884/) (2019)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [MiVOLO: Multi-input Transformer for Age and Gender Estimation](https://mlsanity.com/paper/2307.04616/) (2023)
- [SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation](https://mlsanity.com/paper/2308.11509/) (2023)
- [Masked Contrastive Graph Representation Learning for Age Estimation](https://mlsanity.com/paper/2306.17798/) (2023)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Deep Differentiable Random Forests for Age Estimation](https://mlsanity.com/paper/1907.10665/) (2019)
- [Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion](https://mlsanity.com/paper/2112.10167/) (2021)
- [Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion](https://mlsanity.com/paper/2111.10561/) (2021)
- [Age Progression and Regression with Spatial Attention Modules](https://mlsanity.com/paper/1903.02133/) (2019)
- [Hierarchical Attention-based Age Estimation and Bias Estimation](https://mlsanity.com/paper/2103.09882/) (2021)
- [DAA: A Delta Age AdaIN operation for age estimation via binary code transformer](https://mlsanity.com/paper/2303.07929/) (2023)
- [Adaptive Mean-Residue Loss for Robust Facial Age Estimation](https://mlsanity.com/paper/2203.17156/) (2022)
- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [Children Age Group Detection based on Human-Computer Interaction and Time Series Analysis](https://mlsanity.com/paper/2403.04574/) (2024)

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

- [Dorsal Hand Images for Immersive (XR) and Privacy-preserving Age Assurance and Child Safety](https://mlsanity.com/paper/2608.21009/) (2026)

## Abstract (arXiv)

Facial age estimation has achieved considerable success under controlled conditions. However, in unconstrained real-world scenarios, which are often referred to as 'in the wild', age estimation remains challenging, especially when faces are partially occluded, which may obscure their visibility. To address this limitation, we propose a new approach integrating generative adversarial networks (GANs) and transformer architectures to enable robust age estimation from occluded faces. We employ an SN-Patch GAN to effectively remove occlusions, while an Attentive Residual Convolution Module (ARCM), paired with a Swin Transformer, enhances feature representation. Additionally, we introduce a Multi-Task Age Head (MTAH) that combines regression and distribution learning, further improving age estimation under occlusion. Experimental results on the FG-NET, UTKFace, and MORPH datasets demonstrate that our proposed approach surpasses existing state-of-the-art techniques for occluded facial age estimation by achieving an MAE of 3.00, 4.54, and 2.53 years, respectively.