mlsanityData to 7 Oct 2026

Mining bias-target Alignment from Voronoi Cells

arXiv 2305.03691 ↗First posted 5 May 2023cs.LG cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Despite significant research efforts, deep neural networks are still vulnerable to biases: this raises concerns about their fairness and limits their generalization. In this paper, we propose a bias-agnostic approach to mitigate the impact of bias in deep neural networks. Unlike traditional debiasing approaches, we rely on a metric to quantify ``bias alignment/misalignment'' on target classes, and use this information to discourage the propagation of bias-target alignment information through the network. We conduct experiments on several commonly used datasets for debiasing and compare our method to supervised and bias-specific approaches. Our results indicate that the proposed method achieves comparable performance to state-of-the-art supervised approaches, although it is bias-agnostic, even in presence of multiple biases in the same sample.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

31 of 44 references.

References · 31

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019Invariant Risk Minimizationcited by 1,832
  4. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  5. 2019Natural Adversarial Examplescited by 1,401
  6. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  7. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  8. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  10. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  11. 2020Environment Inference for Invariant Learningcited by 306
  12. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 279
19 more
  1. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  2. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  3. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  4. 2019Learning De-biased Representations with Biased Representationscited by 199
  5. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 183
  6. 2018Partial Adversarial Domain Adaptationcited by 127
  7. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  8. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
  9. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  10. 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
  11. 2023Fairlearn: Assessing and Improving Fairness of AI Systemscited by 74
  12. 2022Learning Debiased Classifier with Biased Committeecited by 51
  13. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  14. 2020Fairness Metrics: A Comparative Analysiscited by 45
  15. 2022Unbiased Supervised Contrastive Learningcited by 40
  16. 2022Content and Style Aware Generation of Text-line Images for Handwriting Recognitioncited by 35
  17. 2022Mitigating Dataset Bias by Using Per-sample Gradientcited by 21
  18. 2021InfoFair: Information-Theoretic Intersectional Fairnesscited by 15
  19. 2022Information Removal at the bottleneck in Deep Neural Networkscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Say My Name: a Model's Bias Discovery Frameworkcited by 4
  2. 2025Diffusing DeBias: Synthetic Bias Amplification for Model Debiasingcited by 3
  3. 2024Debiasing surgeon: fantastic weights and how to find themcited by 2
  4. 2024Debiasify: Self-Distillation for Unsupervised Bias Mitigationcited by 0
  5. 2026Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Modelscited by 0