A Coupled Evolutionary Network for Age Estimation
This work addresses age estimation for pattern analysis applications, presenting an incremental improvement over existing label distribution learning methods.
The paper tackles the problem of age estimation from facial images by addressing the lack of training data and complex aging patterns, proposing a Coupled Evolutionary Network that achieves superior results on Morph, ChaLearn15, and MegaAge-Asian datasets.
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.