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

TL;DR

This paper presents a novel multi-task approach combining GANs, transformers, and a specialized age head to improve facial age estimation in occluded, real-world images, outperforming existing methods.

Contribution

It introduces an integrated framework with occlusion removal, enhanced feature extraction, and multi-task learning, advancing age estimation accuracy under challenging conditions.

Findings

Achieves lower MAE on FG-NET, UTKFace, and MORPH datasets.

Outperforms state-of-the-art methods in occluded face age estimation.

Demonstrates robustness to occlusions in unconstrained environments.

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.