# PML: Progressive Margin Loss for Long-tailed Age Classification

arXiv: https://arxiv.org/abs/2103.02140 · HTML: https://mlsanity.com/paper/2103.02140/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 3 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Negative Margin Matters: Understanding Margin in Few-shot Classification](https://mlsanity.com/paper/2003.12060/) (2020)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [Deep Over-sampling Framework for Classifying Imbalanced Data](https://mlsanity.com/paper/1704.07515/) (2017)
- [BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation](https://mlsanity.com/paper/1904.03358/) (2019)
- [Deep Regression Forests for Age Estimation](https://mlsanity.com/paper/1712.07195/) (2017)
- [C3AE: Exploring the Limits of Compact Model for Age Estimation](https://mlsanity.com/paper/1904.05059/) (2019)
- [Personalized Age Progression with Bi-level Aging Dictionary Learning](https://mlsanity.com/paper/1706.01039/) (2017)

## Built on by (most cited first, 30 of 32)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Retrieval Augmented Classification for Long-Tail Visual Recognition](https://mlsanity.com/paper/2202.11233/) (2022)
- [Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition](https://mlsanity.com/paper/2107.09249/) (2021)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Use Your Head: Improving Long-Tail Video Recognition](https://mlsanity.com/paper/2304.01143/) (2023)
- [Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification](https://mlsanity.com/paper/2306.13856/) (2023)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Improving Image Recognition by Retrieving from Web-Scale Image-Text Data](https://mlsanity.com/paper/2304.05173/) (2023)
- [Teach CLIP to Develop a Number Sense for Ordinal Regression](https://mlsanity.com/paper/2408.03574/) (2024)
- [Hierarchical Memory Learning for Fine-Grained Scene Graph Generation](https://mlsanity.com/paper/2203.06907/) (2022)
- [CILF-CIAE: CLIP-driven Image-Language Fusion for Correcting Inverse Age Estimation](https://mlsanity.com/paper/2312.01758/) (2023)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [Training Over-parameterized Models with Non-decomposable Objectives](https://mlsanity.com/paper/2107.04641/) (2021)
- [A Survey of Deep Long-Tail Classification Advancements](https://mlsanity.com/paper/2404.15593/) (2024)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)
- [ELM: Embedding and Logit Margins for Long-Tail Learning](https://mlsanity.com/paper/2204.13208/) (2022)
- [TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation](https://mlsanity.com/paper/2305.08779/) (2023)
- [DAA: A Delta Age AdaIN operation for age estimation via binary code transformer](https://mlsanity.com/paper/2303.07929/) (2023)
- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [General vs. Long-Tailed Age Estimation: An Approach to Kill Two Birds with One Stone](https://mlsanity.com/paper/2307.10129/) (2023)
- [ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces](https://mlsanity.com/paper/2405.16016/) (2024)
- [Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing](https://mlsanity.com/paper/2306.06599/) (2023)
- [P-Age: Pexels Dataset for Robust Spatio-Temporal Apparent Age Classification](https://mlsanity.com/paper/2311.02432/) (2023)
- [LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation](https://mlsanity.com/paper/2502.05423/) (2025)
- [Generalized Category Discovery under the Long-Tailed Distribution](https://mlsanity.com/paper/2506.12515/) (2025)
- [Self-Paced Deep Regression Forests with Consideration of Ranking Fairness](https://mlsanity.com/paper/2112.06455/) (2021)
- [Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification](https://mlsanity.com/paper/2205.12117/) (2022)
- [Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation](https://mlsanity.com/paper/2511.00123/) (2025)
- [Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition](https://mlsanity.com/paper/2606.22416/) (2026)

## Abstract (arXiv)

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.