# Deep Imbalanced Learning for Face Recognition and Attribute Prediction

arXiv: https://arxiv.org/abs/1806.00194 · HTML: https://mlsanity.com/paper/1806.00194/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2018.

## Built on by (most cited first, 30 of 91)

- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Self-supervised Learning is More Robust to Dataset Imbalance](https://mlsanity.com/paper/2110.05025/) (2021)
- [Long-Tailed Recognition via Weight Balancing](https://mlsanity.com/paper/2203.14197/) (2022)
- [ResLT: Residual Learning for Long-tailed Recognition](https://mlsanity.com/paper/2101.10633/) (2021)
- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [RSG: A Simple but Effective Module for Learning Imbalanced Datasets](https://mlsanity.com/paper/2106.09859/) (2021)
- [Understanding Imbalanced Semantic Segmentation Through Neural Collapse](https://mlsanity.com/paper/2301.01100/) (2023)
- [Generalized Parametric Contrastive Learning](https://mlsanity.com/paper/2209.12400/) (2022)
- [OvarNet: Towards Open-vocabulary Object Attribute Recognition](https://mlsanity.com/paper/2301.09506/) (2023)
- [Towards Long-Tailed 3D Detection](https://mlsanity.com/paper/2211.08691/) (2022)
- [Understanding the role of importance weighting for deep learning](https://mlsanity.com/paper/2103.15209/) (2021)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [Long-Tailed Class Incremental Learning](https://mlsanity.com/paper/2210.00266/) (2022)
- [On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond](https://mlsanity.com/paper/2203.09513/) (2022)
- [Subclass-balancing Contrastive Learning for Long-tailed Recognition](https://mlsanity.com/paper/2306.15925/) (2023)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Constructing Balance from Imbalance for Long-tailed Image Recognition](https://mlsanity.com/paper/2208.02567/) (2022)
- [Procrustean Training for Imbalanced Deep Learning](https://mlsanity.com/paper/2104.01769/) (2021)
- [Class-Difficulty Based Methods for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.14499/) (2022)
- [Feature Fusion from Head to Tail for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.06963/) (2023)
- [Class-Distribution-Aware Calibration for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2109.05263/) (2021)
- [Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration](https://mlsanity.com/paper/2406.06818/) (2024)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Simplifying Neural Network Training Under Class Imbalance](https://mlsanity.com/paper/2312.02517/) (2023)
- [Balancing Biases and Preserving Privacy on Balanced Faces in the Wild](https://mlsanity.com/paper/2103.09118/) (2021)
- [FairCal: Fairness Calibration for Face Verification](https://mlsanity.com/paper/2106.03761/) (2021)
- [Region Rebalance for Long-Tailed Semantic Segmentation](https://mlsanity.com/paper/2204.01969/) (2022)

## Abstract (arXiv)

Data for face analysis often exhibit highly-skewed class distribution, i.e., most data belong to a few majority classes, while the minority classes only contain a scarce amount of instances. To mitigate this issue, contemporary deep learning methods typically follow classic strategies such as class re-sampling or cost-sensitive training. In this paper, we conduct extensive and systematic experiments to validate the effectiveness of these classic schemes for representation learning on class-imbalanced data. We further demonstrate that more discriminative deep representation can be learned by enforcing a deep network to maintain inter-cluster margins both within and between classes. This tight constraint effectively reduces the class imbalance inherent in the local data neighborhood, thus carving much more balanced class boundaries locally. We show that it is easy to deploy angular margins between the cluster distributions on a hypersphere manifold. Such learned Cluster-based Large Margin Local Embedding (CLMLE), when combined with a simple k-nearest cluster algorithm, shows significant improvements in accuracy over existing methods on both face recognition and face attribute prediction tasks that exhibit imbalanced class distribution.