A Coupled Evolutionary Network for Age Estimation

TL;DR

This paper introduces a novel Coupled Evolutionary Network that iteratively refines age label distributions and employs slack regression to improve age estimation accuracy across multiple datasets.

Contribution

It proposes a coupled evolutionary framework combining label distribution learning and slack regression, avoiding strong distribution assumptions and utilizing age order information.

Findings

Outperforms existing methods on Morph, ChaLearn15, MegaAge-Asian datasets.

Effectively refines age label distributions through iterative learning.

Utilizes continuous age interval regression for improved accuracy.

Abstract

Age estimation of unknown persons is a challenging pattern analysis task due to the lacking of training data and various aging mechanisms for different people. Label distribution learning-based methods usually make distribution assumptions to simplify age estimation. However, age label distributions are often complex and difficult to be modeled in a parameter way. Inspired by the biological evolutionary mechanism, we propose a Coupled Evolutionary Network (CEN) with two concurrent evolutionary processes: evolutionary label distribution learning and evolutionary slack regression. Evolutionary network learns and refines age label distributions in an iteratively learning way. Evolutionary label distribution learning adaptively learns and constantly refines the age label distributions without making strong assumptions on the distribution patterns. To further utilize the ordered and continuous information of age labels, we accordingly propose an evolutionary slack regression to convert the discrete age label regression into the continuous age interval regression. Experimental results on Morph, ChaLearn15 and MegaAge-Asian datasets show the superiority of our method.