mlsanityData to 7 Oct 2026

Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation

arXiv 2204.09389 ↗First posted 20 Apr 2022cs.CV cs.AI cs.CYcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are highly susceptible to learning biases in visual data. While various methods have been proposed to mitigate such bias, the majority require explicit knowledge of the biases present in the training data in order to mitigate. We argue the relevance of exploring methods which are completely ignorant of the presence of any bias, but are capable of identifying and mitigating them. Furthermore, we propose using Bayesian neural networks with a predictive uncertainty-weighted loss function to dynamically identify potential bias in individual training samples and to weight them during training. We find a positive correlation between samples subject to bias and higher epistemic uncertainties. Finally, we show the method has potential to mitigate visual bias on a bias benchmark dataset and on a real-world face detection problem, and we consider the merits and weaknesses of our approach.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

24 of 36 references.

References · 24

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  4. 2017Deep Bayesian Active Learning with Image Datacited by 812
  5. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  6. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  7. 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
  8. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  9. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  10. 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
  11. 2019Does Object Recognition Work for Everyone?cited by 149
  12. 2019Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learningcited by 145
12 more
  1. 2018Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddingscited by 114
  2. 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
  3. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  4. 2019Striking the Right Balance with Uncertaintycited by 79
  5. 2020Debiasing Skin Lesion Datasets and Models? Not So Fastcited by 43
  6. 2021Consistent Instance False Positive Improves Fairness in Face Recognitioncited by 40
  7. 2019(De)Constructing Bias on Skin Lesion Datasetscited by 30
  8. 2020Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Studycited by 18
  9. 2021Loss-Aversively Fair Classificationcited by 18
  10. 2021Can Active Learning Preemptively Mitigate Fairness Issues?cited by 15
  11. 2019Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Biascited by 11
  12. 2021Feature and Label Embedding Spaces Matter in Addressing Image Classifier Biascited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 2; 2025: 1.

11 papers.

  1. 2023U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentationcited by 11
  2. 2022CAT: Controllable Attribute Translation for Fair Facial Attribute Classificationcited by 6
  3. 2023Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networkscited by 3
  4. 2023Variation of Gender Biases in Visual Recognition Models Before and After Finetuningcited by 2
  5. 2024Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimalitycited by 2
  6. 2024Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applicationscited by 2
  7. 2023SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filteringcited by 1
  8. 2023Bias mitigation techniques in image classification: fair machine learning in human heritage collectionscited by 0
  9. 2023Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Networkcited by 0
  10. 2023Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation taskcited by 0
  11. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0