# Deep Learning for Face Recognition: Pride or Prejudiced?

arXiv: https://arxiv.org/abs/1904.01219 · HTML: https://mlsanity.com/paper/1904.01219/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2019.

## Built on by (most cited first, 25 of 25)

- [Normalizing Flows for Human Pose Anomaly Detection](https://mlsanity.com/paper/2211.10946/) (2022)
- [Py-Feat: Python Facial Expression Analysis Toolbox](https://mlsanity.com/paper/2104.03509/) (2021)
- [Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment](https://mlsanity.com/paper/2302.10908/) (2023)
- [Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets](https://mlsanity.com/paper/2109.03229/) (2021)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Balancing Biases and Preserving Privacy on Balanced Faces in the Wild](https://mlsanity.com/paper/2103.09118/) (2021)
- [Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models](https://mlsanity.com/paper/2108.06581/) (2021)
- [IFBiD: Inference-Free Bias Detection](https://mlsanity.com/paper/2109.04374/) (2021)
- [How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts](https://mlsanity.com/paper/2207.01168/) (2022)
- [Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma](https://mlsanity.com/paper/2304.13680/) (2023)
- [CASIA-Face-Africa: A Large-scale African Face Image Database](https://mlsanity.com/paper/2105.03632/) (2021)
- [Two-Face: Adversarial Audit of Commercial Face Recognition Systems](https://mlsanity.com/paper/2111.09137/) (2021)
- [The Impact of Racial Distribution in Training Data on Face Recognition Bias: A Closer Look](https://mlsanity.com/paper/2211.14498/) (2022)
- [Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention](https://mlsanity.com/paper/2304.02284/) (2023)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation](https://mlsanity.com/paper/2112.09786/) (2021)
- [Explaining Bias in Deep Face Recognition via Image Characteristics](https://mlsanity.com/paper/2208.11099/) (2022)
- [Exploring Pose-Based Anomaly Detection for Retail Security: A Real-World Shoplifting Dataset and Benchmark](https://mlsanity.com/paper/2501.06591/) (2025)
- [A Quantitative Evaluation of the Expressivity of BMI, Pose and Gender in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2503.06451/) (2025)
- [Harnessing Geometric Constraints from Emotion Labels to improve Face Verification](https://mlsanity.com/paper/2103.03862/) (2021)
- [Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space](https://mlsanity.com/paper/2108.10265/) (2021)
- [Mask-up: Investigating Biases in Face Re-identification for Masked Faces](https://mlsanity.com/paper/2402.13771/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [Reliable and Reproducible Demographic Inference for Fairness in Face Analysis](https://mlsanity.com/paper/2510.20482/) (2025)
- [AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification](https://mlsanity.com/paper/2604.27218/) (2026)

## Abstract (arXiv)

Do very high accuracies of deep networks suggest pride of effective AI or are deep networks prejudiced? Do they suffer from in-group biases (own-race-bias and own-age-bias), and mimic the human behavior? Is in-group specific information being encoded sub-consciously by the deep networks? This research attempts to answer these questions and presents an in-depth analysis of `bias' in deep learning based face recognition systems. This is the first work which decodes if and where bias is encoded for face recognition. Taking cues from cognitive studies, we inspect if deep networks are also affected by social in- and out-group effect. Networks are analyzed for own-race and own-age bias, both of which have been well established in human beings. The sub-conscious behavior of face recognition models is examined to understand if they encode race or age specific features for face recognition. Analysis is performed based on 36 experiments conducted on multiple datasets. Four deep learning networks either trained from scratch or pre-trained on over 10M images are used. Variations across class activation maps and feature visualizations provide novel insights into the functioning of deep learning systems, suggesting behavior similar to humans. It is our belief that a better understanding of state-of-the-art deep learning networks would enable researchers to address the given challenge of bias in AI, and develop fairer systems.