mlsanityData to 14 Oct 2026

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

arXiv 2108.06581 ↗First posted 14 Aug 2021cs.CVcited by 11

Not on the map. Why?

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.

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

22 of 43 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Squeeze-and-Excitation Networkscited by 4,789
  3. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 267
  4. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  5. 2019From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Qualitycited by 223
  6. 2019Learning De-biased Representations with Biased Representationscited by 199
  7. 2019Image Processing Using Multi-Code GAN Priorcited by 185
  8. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
  9. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  10. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 119
  11. 2020Demographic Bias in Biometrics: A Survey on an Emerging Challengecited by 93
  12. 2019UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environmentscited by 84
10 more
  1. 2018Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attackscited by 31
  2. 2020Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognitioncited by 31
  3. 2018An Experimental Evaluation of Covariates Effects on Unconstrained Face Verificationcited by 28
  4. 2019Deep Learning for Face Recognition: Pride or Prejudiced?cited by 25
  5. 2016How Image Degradations Affect Deep CNN-based Face Recognition?cited by 20
  6. 2017Strengths and Weaknesses of Deep Learning Models for Face Recognition Against Image Degradationscited by 19
  7. 2018Visual Psychophysics for Making Face Recognition Algorithms More Explainablecited by 19
  8. 2019Algorithmic Discrimination: Formulation and Exploration in Deep Learning-based Face Biometricscited by 19
  9. 2021NTIRE 2021 Challenge on Perceptual Image Quality Assessmentcited by 18
  10. 2020Identity Enhanced Residual Image Denoisingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 3; 2024: 1; 2025: 0; 2026: 1.

11 papers.

  1. 2021Anatomizing Bias in Facial Analysiscited by 18
  2. 2023Racial Bias within Face Recognition: A Surveycited by 9
  3. 2022Explaining Bias in Deep Face Recognition via Image Characteristicscited by 6
  4. 2022Does lossy image compression affect racial bias within face recognition?cited by 5
  5. 2022Robustness Disparities in Face Detectioncited by 5
  6. 2022Are Face Detection Models Biased?cited by 3
  7. 2024Breaking the Global North Stereotype: A Global South-centric Benchmark Dataset for Auditing and Mitigating Biases in Facial Recognition Systemscited by 3
  8. 2022The More Secure, The Less Equally Usable: Gender and Ethnicity (Un)fairness of Deep Face Recognition along Security Thresholdscited by 2
  9. 2023(Un)fair Exposure in Deep Face Rankings at a Distancecited by 1
  10. 2023What's color got to do with it? Face recognition in grayscalecited by 1
  11. 2026Unbiased Model Prediction Without Using Protected Attribute Informationcited by 0