mlsanityData to 14 Oct 2026

CAT: Controllable Attribute Translation for Fair Facial Attribute Classification

arXiv 2209.06850 ↗First posted 14 Sep 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from both protected attribute level and facial attribute level, which makes it challenging to construct a multi-attribute-level balanced real dataset. To bridge the gap, we propose an effective pipeline to generate high-quality and sufficient facial images with desired facial attributes and supplement the original dataset to be a balanced dataset at both levels, which theoretically satisfies several fairness criteria. The effectiveness of our method is verified on sex classification and facial attribute classification by yielding comparable task performance as the original dataset and further improving fairness in a comprehensive fairness evaluation with a wide range of metrics. Furthermore, our method outperforms both resampling and balanced dataset construction to address dataset bias, and debiasing models to address task bias.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 52 of its 79 references that are in the map. First posted on arXiv 14 Sep 2022.

Builds on

52 of 79 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  8. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  9. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  10. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  12. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
38 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  3. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  4. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  5. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  6. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  7. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  8. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 196
  9. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  10. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  11. 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
  12. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
  13. 2020Fair Attribute Classification through Latent Space De-biasingcited by 125
  14. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 120
  15. 2021Generative Adversarial Transformerscited by 120
  16. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  17. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  18. 2019Fair Generative Modeling via Weak Supervisioncited by 114
  19. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  20. 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
  21. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 104
  22. 2021A Comprehensive Study on Face Recognition Biases Beyond Demographicscited by 86
  23. 2020Face Recognition: Too Bias, or Not Too Bias?cited by 82
  24. 2020Mitigating Face Recognition Bias via Group Adaptive Classifiercited by 67
  25. 2020Towards causal benchmarking of bias in face analysis algorithmscited by 64
  26. 2021Directional Bias Amplificationcited by 54
  27. 2020Biometric Quality: Review and Application to Face Recognition with FaceQnetcited by 42
  28. 2018Fairness GANcited by 32
  29. 2021Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimizationcited by 32
  30. 2018Feature-Wise Bias Amplificationcited by 31
  31. 2020Contrastive Examples for Addressing the Tyranny of the Majoritycited by 21
  32. 2019Invariant Representations through Adversarial Forgettingcited by 20
  33. 2017Data Augmentation in Emotion Classification Using Generative Adversarial Networkscited by 19
  34. 2021On the Applicability of Synthetic Data for Face Recognitioncited by 15
  35. 2020Towards Threshold Invariant Fair Classificationcited by 12
  36. 2022Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigationcited by 11
  37. 2017Bidirectional Conditional Generative Adversarial Networkscited by 10
  38. 2021Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognitioncited by 5

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 2.

6 papers.

  1. 2024Fairness and Bias Mitigation in Computer Vision: A Surveycited by 13
  2. 2023Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groupscited by 6
  3. 2023Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networkscited by 3
  4. 2023SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filteringcited by 1
  5. 2025Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regressioncited by 1
  6. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0