# Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

arXiv: https://arxiv.org/abs/2207.10077 · HTML: https://mlsanity.com/paper/2207.10077/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 79 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 30 of 63)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (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)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Environment Inference for Invariant Learning](https://mlsanity.com/paper/2010.07249/) (2020)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)

## Built on by (most cited first, 30 of 47)

- [Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.17591/) (2023)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others](https://mlsanity.com/paper/2212.04825/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases](https://mlsanity.com/paper/2303.05470/) (2023)
- [Overcoming Simplicity Bias in Deep Networks using a Feature Sieve](https://mlsanity.com/paper/2301.13293/) (2023)
- [Men Also Do Laundry: Multi-Attribute Bias Amplification](https://mlsanity.com/paper/2210.11924/) (2022)
- [Identification of Systematic Errors of Image Classifiers on Rare Subgroups](https://mlsanity.com/paper/2303.05072/) (2023)
- [Discover and Mitigate Multiple Biased Subgroups in Image Classifiers](https://mlsanity.com/paper/2403.12777/) (2024)
- [Self-supervised debiasing using low rank regularization](https://mlsanity.com/paper/2210.05248/) (2022)
- [Efficient Bias Mitigation Without Privileged Information](https://mlsanity.com/paper/2409.17691/) (2024)
- [Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness](https://mlsanity.com/paper/2310.06161/) (2023)
- [Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition](https://mlsanity.com/paper/2502.15809/) (2025)
- [Fairness-aware Vision Transformer via Debiased Self-Attention](https://mlsanity.com/paper/2301.13803/) (2023)
- [Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization](https://mlsanity.com/paper/2409.03303/) (2024)
- [Mining bias-target Alignment from Voronoi Cells](https://mlsanity.com/paper/2305.03691/) (2023)
- [BAdd: Bias Mitigation through Bias Addition](https://mlsanity.com/paper/2408.11439/) (2024)
- [MAVias: Mitigate any Visual Bias](https://mlsanity.com/paper/2412.06632/) (2024)
- [Identifying Systematic Errors in Object Detectors with the SCROD Pipeline](https://mlsanity.com/paper/2309.13489/) (2023)
- [Say My Name: a Model's Bias Discovery Framework](https://mlsanity.com/paper/2408.09570/) (2024)
- [Sebra: Debiasing Through Self-Guided Bias Ranking](https://mlsanity.com/paper/2501.18277/) (2025)
- [Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers](https://mlsanity.com/paper/2504.20902/) (2025)
- [How I Met Your Bias: Investigating Bias Amplification in Diffusion Models](https://mlsanity.com/paper/2512.20233/) (2025)
- [Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts](https://mlsanity.com/paper/2308.10005/) (2023)
- [Evaluating Model Bias Requires Characterizing its Mistakes](https://mlsanity.com/paper/2407.10633/) (2024)
- [Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing](https://mlsanity.com/paper/2502.09564/) (2025)
- [Attention IoU: Examining Biases in CelebA using Attention Maps](https://mlsanity.com/paper/2503.19846/) (2025)
- [Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber](https://mlsanity.com/paper/2305.04043/) (2023)

## Abstract (arXiv)

Deep image classifiers have been found to learn biases from datasets. To mitigate the biases, most previous methods require labels of protected attributes (e.g., age, skin tone) as full-supervision, which has two limitations: 1) it is infeasible when the labels are unavailable; 2) they are incapable of mitigating unknown biases -- biases that humans do not preconceive. To resolve those problems, we propose Debiasing Alternate Networks (DebiAN), which comprises two networks -- a Discoverer and a Classifier. By training in an alternate manner, the discoverer tries to find multiple unknown biases of the classifier without any annotations of biases, and the classifier aims at unlearning the biases identified by the discoverer. While previous works evaluate debiasing results in terms of a single bias, we create Multi-Color MNIST dataset to better benchmark mitigation of multiple biases in a multi-bias setting, which not only reveals the problems in previous methods but also demonstrates the advantage of DebiAN in identifying and mitigating multiple biases simultaneously. We further conduct extensive experiments on real-world datasets, showing that the discoverer in DebiAN can identify unknown biases that may be hard to be found by humans. Regarding debiasing, DebiAN achieves strong bias mitigation performance.