Adaptive Mean-Residue Loss for Robust Facial Age Estimation

TL;DR

This paper introduces an adaptive mean-residue loss function for facial age estimation that improves robustness by leveraging age distribution modeling, outperforming traditional regression and classification methods.

Contribution

It proposes a novel loss function combining mean and residue components to better handle age ambiguity through distribution learning.

Findings

Validated on FG-NET and CLAP2016 datasets

Achieved improved age estimation accuracy

Demonstrated robustness to age ambiguity

Abstract

Automated facial age estimation has diverse real-world applications in multimedia analysis, e.g., video surveillance, and human-computer interaction. However, due to the randomness and ambiguity of the aging process, age assessment is challenging. Most research work over the topic regards the task as one of age regression, classification, and ranking problems, and cannot well leverage age distribution in representing labels with age ambiguity. In this work, we propose a simple yet effective loss function for robust facial age estimation via distribution learning, i.e., adaptive mean-residue loss, in which, the mean loss penalizes the difference between the estimated age distribution's mean and the ground-truth age, whereas the residue loss penalizes the entropy of age probability out of dynamic top-K in the distribution. Experimental results in the datasets FG-NET and CLAP2016 have validated the effectiveness of the proposed loss. Our code is available at https://github.com/jacobzhaoziyuan/AMR-Loss.