# BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers

arXiv: https://arxiv.org/abs/2605.28450 · HTML: https://mlsanity.com/paper/2605.28450/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Learning Robust Representations by Projecting Superficial Statistics Out](https://mlsanity.com/paper/1903.06256/) (2019)
- [Learning Debiased Representation via Disentangled Feature Augmentation](https://mlsanity.com/paper/2107.01372/) (2021)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [Tag2Text: Guiding Vision-Language Model via Image Tagging](https://mlsanity.com/paper/2303.05657/) (2023)
- [Shape-Texture Debiased Neural Network Training](https://mlsanity.com/paper/2010.05981/) (2020)
- [BiaSwap: Removing dataset bias with bias-tailored swapping augmentation](https://mlsanity.com/paper/2108.10008/) (2021)
- [Discovering and Mitigating Visual Biases through Keyword Explanation](https://mlsanity.com/paper/2301.11104/) (2023)
- [Learning Debiased Classifier with Biased Committee](https://mlsanity.com/paper/2206.10843/) (2022)
- [FairRAG: Fair Human Generation via Fair Retrieval Augmentation](https://mlsanity.com/paper/2403.19964/) (2024)
- [Bias Mimicking: A Simple Sampling Approach for Bias Mitigation](https://mlsanity.com/paper/2209.15605/) (2022)
- [SelecMix: Debiased Learning by Contradicting-pair Sampling](https://mlsanity.com/paper/2211.02291/) (2022)
- [Revisiting the Importance of Amplifying Bias for Debiasing](https://mlsanity.com/paper/2205.14594/) (2022)
- [Rethinking Personalized Ranking at Pinterest: An End-to-End Approach](https://mlsanity.com/paper/2209.08435/) (2022)
- [Web-Scale Responsive Visual Search at Bing](https://mlsanity.com/paper/1802.04914/) (2018)
- [Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse](https://mlsanity.com/paper/2405.05587/) (2024)

## Built on by (most cited first, 1 of 1)

- [Text-to-seed generation: Training-free open-vocabulary seeded semantic segmentation via re-purposing diffusion as text-guided seed generator](https://mlsanity.com/paper/2608.26624/) (2026)

## Abstract (arXiv)

Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks are known for their tendency to learn biases present in data. This can reinforce unfairness in web services and the web data, leading to a vicious cycle. In the context of image classification, networks learn bias attributes for a specific class when a majority of images contain the same attribute only for a given class. Hence, training a fair and debiased classifier from a biased dataset demands handling an imbalanced problem between a majority of images with bias attributes (bias-aligned samples) and a minority without (bias-conflict samples). In this work, we introduce BiasEdit, a modular framework that automatically detects bias attributes from the original dataset and edits them to construct a debiased dataset. Specifically, BiasEdit first detects unknown bias attributes via statistical dependence and mutual information analysis of visual-linguistic representations, and then explicitly edits those attributes using text-guided image editing to generate realistic bias-conflict samples. Unlike prior works that assume known bias attributes or relies on synthetic mixing, our method operates without manual annotations and can leverage off-the-shelf vision-language and editing models. BiasEdit addresses a fundamental challenge in Web-sourced visual AI, mitigating dataset-induced bias and achieving state-of-the-art debiasing performance even when training data are fully biased.