mlsanityData to 7 Oct 2026

BAdd: Bias Mitigation through Bias Addition

arXiv 2408.11439 ↗First posted 21 Aug 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Computer vision (CV) datasets often exhibit biases that are perpetuated by deep learning models. While recent efforts aim to mitigate these biases and foster fair representations, they fail in complex real-world scenarios. In particular, existing methods excel in controlled experiments involving benchmarks with single-attribute injected biases, but struggle with multi-attribute biases being present in well-established CV datasets. Here, we introduce BAdd, a simple yet effective method that allows for learning fair representations invariant to the attributes introducing bias by incorporating features representing these attributes into the backbone. BAdd is evaluated on seven benchmarks and exhibits competitive performance, surpassing state-of-the-art methods on both single- and multi-attribute benchmarks. Notably, BAdd achieves +27.5% and +5.5% absolute accuracy improvements on the challenging multi-attribute benchmarks, FB-Biased-MNIST and CelebA, respectively.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

33 of 47 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2018SlowFast Networks for Video Recognitioncited by 1,862
  5. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  6. 2017Generative Adversarial Networks: An Overviewcited by 588
  7. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  8. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  9. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  10. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 279
  11. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  12. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
21 more
  1. 2019Learning De-biased Representations with Biased Representationscited by 199
  2. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 183
  3. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  4. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  5. 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
  6. 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
  7. 2022A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Otherscited by 85
  8. 2021A Survey on Bias in Visual Datasetscited by 84
  9. 2018Learning Controllable Fair Representationscited by 83
  10. 2023Discover and Cure: Concept-aware Mitigation of Spurious Correlationcited by 71
  11. 2023Simple and Fast Group Robustness by Automatic Feature Reweightingcited by 68
  12. 2023Discovering and Mitigating Visual Biases through Keyword Explanationcited by 58
  13. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  14. 2022Unbiased Supervised Contrastive Learningcited by 40
  15. 2017Examining CNN Representations with respect to Dataset Biascited by 27
  16. 2020FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognitioncited by 26
  17. 2022Mitigating Dataset Bias by Using Per-sample Gradientcited by 21
  18. 2023FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associationscited by 18
  19. 2023Towards Fair Face Verification: An In-depth Analysis of Demographic Biasescited by 14
  20. 2022OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypothesescited by 11
  21. 2024Language-guided Detection and Mitigation of Unknown Dataset Biascited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2024MAVias: Mitigate any Visual Biascited by 5
  2. 2025VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigationcited by 2
  3. 2025Multi Attribute Bias Mitigation via Representation Learningcited by 0
  4. 2026Face Age Verification Vulnerabilities Under Simple Appearance Manipulationscited by 0
  5. 2026Scaling Vision-Language Models Is Not Enough to Mitigate Biascited by 0