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

2025/06/16 by Waqar Tanveer, Laura Fernández-Robles, Tanveer, Waqar +7
Computer Science · Social Sciences · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Face recognition and analysis #Image and Video Processing (eess.IV) #Technology Use by Older Adults #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.13445

openalex publication_date 2025/06/16 · openalex created_date 2025/10/13 · openalex updated_date 2026/07/30

Abstract

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.

Citations

• GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization
• SwinFace: A Multi-Task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation
• MiVOLO: Multi-input Transformer for Age and Gender Estimation
• Masked Contrastive Graph Representation Learning for Age Estimation
• DAA: A Delta Age AdaIN operation for age estimation via binary code transformer
• Moving Window Regression: A Novel Approach to Ordinal Regression
• Teacher-Student Training and Triplet Loss to Reduce the Effect of\n Drastic Face Occlusion
• FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild
• Hierarchical Attention-based Age Estimation and Bias Estimation
• Delving into Deep Imbalanced Regression
• Transformers in Vision: A Survey
• Deep Differentiable Random Forests for Age Estimation
• Age Progression and Regression with Spatial Attention Modules
• Rank consistent ordinal regression for neural networks with application to age estimation
• Free-Form Image Inpainting with Gated Convolution
• Attention Is All You Need
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Label Distribution Learning
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Cited by

• Underage Detection through a Multi-Task and MultiAge Approach for Screening Minors in Unconstrained Imagery

Related

• Continuous Face Aging via Self-estimated Residual Age Embedding
• FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild
• Fusion Network for Face-based Age Estimation
• Hierarchical Attention-based Age Estimation and Bias Estimation
• Apparent Age Estimation Using Ensemble of Deep Learning Models