# PML: Progressive Margin Loss for Long-tailed Age Classification Source: [PML: Progressive Margin Loss for Long-tailed Age Classification]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:04:58.222Z Authors: Zongyong Deng, Hao Liu, Yaoxing Wang, Chenyang Wang, Zekuan Yu, Xuehong Sun Published: 2021-03-03T02:47:09.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Age Estimation on FG-NET](): Age Estimation; FG-NET; MAE: 2.16. - [Facial Age Classification on ChaLearn LAP 2015 (val test)](): Facial Age Classification; ChaLearn LAP 2015 (val test); MAE: 2.915. - [Age Estimation on Morph (test)](): Age Estimation; Morph (test); MAE (Years): 2.15. - [Age Estimation on MORPH S2 (Setting II)](): Age Estimation; MORPH S2 (Setting II); MAE: 2.31. - [Age estimation on MORPH II (Setting I)](): Age Estimation; MORPH II (Setting I); MAE: 2.15. - [Age Estimation on Morph Intra-Dataset 5](): Age Estimation; Morph Intra-Dataset 5; MAE: 2.15. - [Apparent Age Estimation on ChaLearn 2015 (val)](): Apparent Age Estimation; ChaLearn 2015 (val); Epsilon Error: 29.3. ## Original sources and implementation [Original paper]() [PDF]()