# Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network

arXiv: https://arxiv.org/abs/2303.16564 · HTML: https://mlsanity.com/paper/2303.16564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 30 of 35)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [The Pitfalls of Simplicity Bias in Neural Networks](https://mlsanity.com/paper/2006.07710/) (2020)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks](https://mlsanity.com/paper/2002.10118/) (2020)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (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)
- [Learning from others' mistakes: Avoiding dataset biases without modeling them](https://mlsanity.com/paper/2012.01300/) (2020)
- [Striking the Right Balance with Uncertainty](https://mlsanity.com/paper/1901.07590/) (2019)
- [Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction](https://mlsanity.com/paper/1807.00199/) (2018)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Learning Debiased Classifier with Biased Committee](https://mlsanity.com/paper/2206.10843/) (2022)
- [Consistent Instance False Positive Improves Fairness in Face Recognition](https://mlsanity.com/paper/2106.05519/) (2021)
- [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)
- [Are Bias Mitigation Techniques for Deep Learning Effective?](https://mlsanity.com/paper/2104.00170/) (2021)

## Abstract (arXiv)

The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual datasets. Due to the difficulty and variability of the task, no single de-biasing method has been universally successful. In particular, implicit methods not requiring explicit knowledge of bias variables are especially relevant for real-world applications. We propose a novel implicit mitigation method using a Bayesian neural network, allowing us to leverage the relationship between epistemic uncertainties and the presence of bias or spurious correlations in a sample. Our proposed posterior estimate sharpening procedure encourages the network to focus on core features that do not contribute to high uncertainties. Experimental results on three benchmark datasets demonstrate that Bayesian networks with sharpened posterior estimates perform comparably to prior existing methods and show potential worthy of further exploration.