mlsanityData to 14 Oct 2026

On Biased Behavior of GANs for Face Verification

arXiv 2208.13061 ↗First posted 27 Aug 2022cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep Learning systems need large data for training. Datasets for training face verification systems are difficult to obtain and prone to privacy issues. Synthetic data generated by generative models such as GANs can be a good alternative. However, we show that data generated from GANs are prone to bias and fairness issues. Specifically, GANs trained on FFHQ dataset show biased behavior towards generating white faces in the age group of 20-29. We also demonstrate that synthetic faces cause disparate impact, specifically for race attribute, when used for fine tuning face verification systems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 27 Aug 2022.

Builds on

16 of 30 references.

References · 16

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  3. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  4. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 220
  5. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  6. 2020Face Recognition: Too Bias, or Not Too Bias?cited by 82
  7. 2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 74
  8. 2022Fair Contrastive Learning for Facial Attribute Classificationcited by 71
  9. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  10. 2014Surpassing Human-Level Face Verification Performance on LFW with GaussianFacecited by 24
  11. 2019Characterizing Bias in Classifiers using Generative Modelscited by 23
  12. 2021Learning Facial Representations from the Cycle-consistency of Facecited by 20
4 more
  1. 2022FairStyle: Debiasing StyleGAN2 with Style Channel Manipulationscited by 20
  2. 2022Evaluation-oriented Knowledge Distillation for Deep Face Recognitioncited by 19
  3. 2022Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptationcited by 7
  4. 2022Learn to Cluster Faces via Pairwise Classificationcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Bias mitigation techniques in image classification: fair machine learning in human heritage collectionscited by 0