General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone

TL;DR

This paper introduces GLAE, a unified training framework for facial age estimation that effectively balances performance on both general and long-tailed datasets, achieving state-of-the-art results.

Contribution

The paper proposes a novel, simple, and flexible training paradigm called GLAE that improves age estimation accuracy for both common and rare age groups simultaneously.

Findings

Lowest MAE and CMAE on Morph II dataset

Up to 34% reduction in MAE compared to previous methods

Outperforms state-of-the-art on multiple benchmark datasets

Abstract

Facial age estimation has received a lot of attention for its diverse application scenarios. Most existing studies treat each sample equally and aim to reduce the average estimation error for the entire dataset, which can be summarized as General Age Estimation. However, due to the long-tailed distribution prevalent in the dataset, treating all samples equally will inevitably bias the model toward the head classes (usually the adult with a majority of samples). Driven by this, some works suggest that each class should be treated equally to improve performance in tail classes (with a minority of samples), which can be summarized as Long-tailed Age Estimation. However, Long-tailed Age Estimation usually faces a performance trade-off, i.e., achieving improvement in tail classes by sacrificing the head classes. In this paper, our goal is to design a unified framework to perform well on both tasks, killing two birds with one stone. To this end, we propose a simple, effective, and flexible training paradigm named GLAE, which is two-fold. Our GLAE provides a surprising improvement on Morph II, reaching the lowest MAE and CMAE of 1.14 and 1.27 years, respectively. Compared to the previous best method, MAE dropped by up to 34%, which is an unprecedented improvement, and for the first time, MAE is close to 1 year old. Extensive experiments on other age benchmark datasets, including CACD, MIVIA, and Chalearn LAP 2015, also indicate that GLAE outperforms the state-of-the-art approaches significantly.