# Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models

arXiv: https://arxiv.org/abs/2108.06581 · HTML: https://mlsanity.com/paper/2108.06581/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 14 Aug 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Understanding How Image Quality Affects Deep Neural Networks](https://mlsanity.com/paper/1604.04004/) (2016)
- [Demographic Bias in Biometrics: A Survey on an Emerging Challenge](https://mlsanity.com/paper/2003.02488/) (2020)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks](https://mlsanity.com/paper/1803.00401/) (2018)
- [Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognition](https://mlsanity.com/paper/2004.01019/) (2020)
- [An Experimental Evaluation of Covariates Effects on Unconstrained Face Verification](https://mlsanity.com/paper/1808.05508/) (2018)
- [Deep Learning for Face Recognition: Pride or Prejudiced?](https://mlsanity.com/paper/1904.01219/) (2019)
- [How Image Degradations Affect Deep CNN-based Face Recognition?](https://mlsanity.com/paper/1608.05246/) (2016)
- [Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradations](https://mlsanity.com/paper/1710.01494/) (2017)
- [Visual Psychophysics for Making Face Recognition Algorithms More Explainable](https://mlsanity.com/paper/1803.07140/) (2018)
- [Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometrics](https://mlsanity.com/paper/1912.01842/) (2019)
- [NTIRE 2021 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2105.03072/) (2021)
- [Identity Enhanced Residual Image Denoising](https://mlsanity.com/paper/2004.13523/) (2020)

## Built on by (most cited first, 11 of 11)

- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [Explaining Bias in Deep Face Recognition via Image Characteristics](https://mlsanity.com/paper/2208.11099/) (2022)
- [Does lossy image compression affect racial bias within face recognition?](https://mlsanity.com/paper/2208.07613/) (2022)
- [Robustness Disparities in Face Detection](https://mlsanity.com/paper/2211.15937/) (2022)
- [Are Face Detection Models Biased?](https://mlsanity.com/paper/2211.03588/) (2022)
- [Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systems](https://mlsanity.com/paper/2407.15810/) (2024)
- [The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholds](https://mlsanity.com/paper/2209.15550/) (2022)
- [(Un)fair Exposure in Deep Face Rankings at a Distance](https://mlsanity.com/paper/2308.11732/) (2023)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Unbiased Model Prediction Without Using Protected Attribute Information](https://mlsanity.com/paper/2603.29270/) (2026)

## Abstract (arXiv)

Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation provide equal and unbiased performance across subgroups. However, textitcan seemingly unbiased pre-trained model become biased when input data undergoes certain distortions? For the first time, we attempt to answer this question in the context of face recognition. We provide a systematic analysis to evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions across different textitgender and textitrace subgroups. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.