Learning nonlinear distance functions using neural network for regression with application to robust human age estimation

Abstract

In this paper, a robust regression method is proposed for human age estimation, in which, outlier samples are corrected by their neighbors, through asymptotically increasing the correlation coefficients between the desired distances and the distances of sample labels. As another extension, we adopt a nonlinear distance function and approximate it by neural network. For fair comparison, we also experiment on the regression problem of age estimation from face images, and the results are very competitive among the state of the art.