PML: Progressive Margin Loss for Long-tailed Age Classification

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 art. Code will be made publicly.

Automated summary

In this paper, a progressive margin loss (PML) approach for unconstrained facial age classification is proposed, aiming to adaptively refine the age label pattern by enforcing margins that consider the in-between discrepancy of intra-class variance, inter-class variance, and class center. The PML incorporates ordinal and variational margins, along with a globally-tuned deep neural network paradigm, achieving compelling performance compared to state-of-the-art methods on three face aging datasets.