# Improving Fairness in Image Classification via Sketching

arXiv: https://arxiv.org/abs/2211.00168 · HTML: https://mlsanity.com/paper/2211.00168/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Multiaccuracy: Black-Box Post-Processing for Fairness in Classification](https://mlsanity.com/paper/1805.12317/) (2018)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging](https://mlsanity.com/paper/2105.14021/) (2021)
- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [Bias Mitigation Post-processing for Individual and Group Fairness](https://mlsanity.com/paper/1812.06135/) (2018)
- [Photo-Sketching: Inferring Contour Drawings from Images](https://mlsanity.com/paper/1901.00542/) (2019)
- [Learning to Sketch with Shortcut Cycle Consistency](https://mlsanity.com/paper/1805.00247/) (2018)
- [Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models](https://mlsanity.com/paper/2203.01584/) (2022)
- [Creative Sketch Generation](https://mlsanity.com/paper/2011.10039/) (2020)
- [Quantifying Societal Bias Amplification in Image Captioning](https://mlsanity.com/paper/2203.15395/) (2022)
- [Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing](https://mlsanity.com/paper/2007.13632/) (2020)

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

- [FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification](https://mlsanity.com/paper/2303.08325/) (2023)
- [Model-Agnostic Gender Debiased Image Captioning](https://mlsanity.com/paper/2304.03693/) (2023)
- [Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2405.08681/) (2024)
- [A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models](https://mlsanity.com/paper/2401.03695/) (2024)
- [Generative AI in Depth: A Survey of Recent Advances, Model Variants, and Real-World Applications](https://mlsanity.com/paper/2510.21887/) (2025)
- [Open Vocabulary Semantic Scene Sketch Understanding](https://mlsanity.com/paper/2312.12463/) (2023)
- [Debiased Noise Editing on Foundation Models for Fair Medical Image Classification](https://mlsanity.com/paper/2403.06104/) (2024)
- [APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation](https://mlsanity.com/paper/2403.05114/) (2024)
- [Evaluating Fairness and Mitigating Bias in Machine Learning: A Novel Technique using Tensor Data and Bayesian Regression](https://mlsanity.com/paper/2506.11627/) (2025)
- [Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback](https://mlsanity.com/paper/2407.09551/) (2024)
- [Component-Based Fairness in Face Attribute Classification with Bayesian Network-informed Meta Learning](https://mlsanity.com/paper/2505.01699/) (2025)

## Abstract (arXiv)

Fairness is a fundamental requirement for trustworthy and human-centered Artificial Intelligence (AI) system. However, deep neural networks (DNNs) tend to make unfair predictions when the training data are collected from different sub-populations with different attributes (i.e. color, sex, age), leading to biased DNN predictions. We notice that such a troubling phenomenon is often caused by data itself, which means that bias information is encoded to the DNN along with the useful information (i.e. class information, semantic information). Therefore, we propose to use sketching to handle this phenomenon. Without losing the utility of data, we explore the image-to-sketching methods that can maintain useful semantic information for the target classification while filtering out the useless bias information. In addition, we design a fair loss to further improve the model fairness. We evaluate our method through extensive experiments on both general scene dataset and medical scene dataset. Our results show that the desired image-to-sketching method improves model fairness and achieves satisfactory results among state-of-the-art.