mlsanityData to 14 Oct 2026

Enhancing Fairness of Visual Attribute Predictors

arXiv 2207.05727 ↗First posted 7 Jul 2022cs.CV math.PRcited by 3

Not on the map. Why?

Abstract (arXiv)

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware regularization losses based on batch estimates of Demographic Parity, Equalized Odds, and a novel Intersection-over-Union measure. The experiments performed on facial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanoma classification challenge show the effectiveness of our proposed fairness losses for bias mitigation as they improve model fairness while maintaining high classification performance. To the best of our knowledge, our work is the first attempt to incorporate these types of losses in an end-to-end training scheme for mitigating biases of visual attribute predictors. Our code is available at https://github.com/nish03/FVAP.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 52 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

33 of 52 references.

References · 33

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  4. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  5. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  6. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  7. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  8. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  9. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  10. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  11. 2020A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Contextcited by 146
  12. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
21 more
  1. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  2. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  3. 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
  4. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  5. 2020Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditingcited by 89
  6. 2019Diversity in Facescited by 77
  7. 2019Image Counterfactual Sensitivity Analysis for Detecting Unintended Biascited by 74
  8. 2020Mitigating Face Recognition Bias via Group Adaptive Classifiercited by 67
  9. 2021Fair Feature Distillation for Visual Recognitioncited by 59
  10. 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
  11. 2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
  12. 2021PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognitioncited by 38
  13. 2020Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulationcited by 37
  14. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31
  15. 2019Characterizing Bias in Classifiers using Generative Modelscited by 23
  16. 2021Algorithm Fairness in AI for Medicine and Healthcarecited by 21
  17. 2021FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentationcited by 19
  18. 2021Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversarycited by 14
  19. 2020Fair Meta-Learning For Few-Shot Classificationcited by 13
  20. 2019Slim-CNN: A Light-Weight CNN for Face Attribute Predictioncited by 11
  21. 2018Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Networkcited by 7

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024Distributionally Generative Augmentation for Fair Facial Attribute Classificationcited by 8
  2. 2025pFedFair: Towards Optimal Group Fairness-Accuracy Trade-off in Heterogeneous Federated Learningcited by 1
  3. 2025Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regressioncited by 1