Joint Gender Classification and Age Estimation by Nearly Orthogonalizing Their Semantic Spaces

TL;DR

This paper introduces a novel joint learning framework for gender classification and age estimation that leverages near-orthogonality of their semantic spaces, improving performance on multiple datasets.

Contribution

It proposes a new semantic regularization approach for joint gender and age estimation, including kernelized nonlinear extension, demonstrating superior results.

Findings

Effective joint learning of gender and age estimation.

Outperforms existing methods on three aging datasets.

Kernelized nonlinear model enhances accuracy.

Abstract

In human face-based biometrics, gender classification and age estimation are two typical learning tasks. Although a variety of approaches have been proposed to handle them, just a few of them are solved jointly, even so, these joint methods do not yet specifically concern the semantic difference between human gender and age, which is intuitively helpful for joint learning, consequently leaving us a room of further improving the performance. To this end, in this work we firstly propose a general learning framework for jointly estimating human gender and age by specially attempting to formulate such semantic relationships as a form of near-orthogonality regularization and then incorporate it into the objective of the joint learning framework. In order to evaluate the effectiveness of the proposed framework, we exemplify it by respectively taking the widely used binary-class SVM for gender classification, and two threshold-based ordinal regression methods (i.e., the discriminant learning for ordinal regression and support vector ordinal regression) for age estimation, and crucially coupling both through the proposed semantic formulation. Moreover, we develop its kernelized nonlinear counterpart by deriving a representer theorem for the joint learning strategy. Finally, through extensive experiments on three aging datasets FG-NET, Morph Album I and Morph Album II, we demonstrate the effectiveness and superiority of the proposed joint learning strategy.