# Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation

arXiv: https://arxiv.org/abs/2204.09389 · HTML: https://mlsanity.com/paper/2204.09389/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 24 of 24)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age](https://mlsanity.com/paper/1908.04913/) (2019)
- [Striking the Right Balance with Uncertainty](https://mlsanity.com/paper/1901.07590/) (2019)
- [Debiasing Skin Lesion Datasets and Models? Not So Fast](https://mlsanity.com/paper/2004.11457/) (2020)
- [Consistent Instance False Positive Improves Fairness in Face Recognition](https://mlsanity.com/paper/2106.05519/) (2021)
- [(De)Constructing Bias on Skin Lesion Datasets](https://mlsanity.com/paper/1904.08818/) (2019)
- [Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study](https://mlsanity.com/paper/2005.07302/) (2020)
- [Loss-Aversively Fair Classification](https://mlsanity.com/paper/2105.04273/) (2021)
- [Can Active Learning Preemptively Mitigate Fairness Issues?](https://mlsanity.com/paper/2104.06879/) (2021)
- [Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias](https://mlsanity.com/paper/1909.09285/) (2019)
- [Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias](https://mlsanity.com/paper/2110.14336/) (2021)

## Built on by (most cited first, 11 of 11)

- [U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation](https://mlsanity.com/paper/2307.09947/) (2023)
- [CAT: Controllable Attribute Translation for Fair Facial Attribute Classification](https://mlsanity.com/paper/2209.06850/) (2022)
- [Variation of Gender Biases in Visual Recognition Models Before and After Finetuning](https://mlsanity.com/paper/2303.07615/) (2023)
- [Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks](https://mlsanity.com/paper/2310.04955/) (2023)
- [Enhancing Fairness and Performance in Machine Learning Models: A Multi-Task Learning Approach with Monte-Carlo Dropout and Pareto Optimality](https://mlsanity.com/paper/2404.08230/) (2024)
- [Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications](https://mlsanity.com/paper/2407.16953/) (2024)
- [SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering](https://mlsanity.com/paper/2311.07141/) (2023)
- [Bias mitigation techniques in image classification: fair machine learning in human heritage collections](https://mlsanity.com/paper/2303.11449/) (2023)
- [Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network](https://mlsanity.com/paper/2303.16564/) (2023)
- [Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task](https://mlsanity.com/paper/2309.06807/) (2023)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)

## 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.