PML: Progressive Margin Loss for Long-tailed Age Classification

TL;DR

This paper introduces a Progressive Margin Loss (PML) method for facial age classification that adaptively refines age label patterns, improving accuracy especially for underrepresented age groups.

Contribution

The novel PML approach combines ordinal and variational margins to better handle data imbalance and intra/inter-class variance in age classification.

Findings

PML outperforms existing methods on three face aging datasets.

The approach effectively reduces bias in predictions for sparse age classes.

Extensive experiments validate the robustness and efficiency of PML.

Abstract

In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns adequate instances to outline its data distribution, likely leading to bias prediction where the training samples are sparse across age classes. Instead, our PML aims to adaptively refine the age label pattern by enforcing a couple of margins, which fully takes in the in-between discrepancy of the intra-class variance, inter-class variance and class center. Our PML typically incorporates with the ordinal margin and the variational margin, simultaneously plugging in the globally-tuned deep neural network paradigm. More specifically, the ordinal margin learns to exploit the correlated relationship of the real-world age labels. Accordingly, the variational margin is leveraged to minimize the influence of head classes that misleads the prediction of tailed samples. Moreover, our optimization carefully seeks a series of indicator curricula to achieve robust and efficient model training. Extensive experimental results on three face aging datasets demonstrate that our PML achieves compelling performance compared to state of the arts. Code will be made publicly.