# Toward Fairness Through Fair Multi-Exit Framework for Dermatological Disease Diagnosis

arXiv: https://arxiv.org/abs/2306.14518 · HTML: https://mlsanity.com/paper/2306.14518/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 26 Jun 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [Fairness in Deep Learning: A Computational Perspective](https://mlsanity.com/paper/1908.08843/) (2019)
- [Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings](https://mlsanity.com/paper/1809.02169/) (2018)
- [Analyzing and Improving Representations with the Soft Nearest Neighbor Loss](https://mlsanity.com/paper/1902.01889/) (2019)
- [Fair Feature Distillation for Visual Recognition](https://mlsanity.com/paper/2106.04411/) (2021)
- [FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2203.02110/) (2022)
- [Bias Remediation in Driver Drowsiness Detection systems using Generative Adversarial Networks](https://mlsanity.com/paper/1912.12123/) (2019)
- [Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generation](https://mlsanity.com/paper/2209.01604/) (2022)
- [Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspective](https://mlsanity.com/paper/2011.02155/) (2020)
- ["One-Shot" Reduction of Additive Artifacts in Medical Images](https://mlsanity.com/paper/2110.12274/) (2021)

## Built on by (most cited first, 14 of 14)

- [Achieve Fairness without Demographics for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2401.08066/) (2024)
- [Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2405.08681/) (2024)
- [Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering](https://mlsanity.com/paper/2410.09380/) (2024)
- [Incorporating Rather Than Eliminating: Achieving Fairness for Skin Disease Diagnosis Through Group-Specific Expert](https://mlsanity.com/paper/2506.17787/) (2025)
- [DermDiff: Generative Diffusion Model for Mitigating Racial Biases in Dermatology Diagnosis](https://mlsanity.com/paper/2503.17536/) (2025)
- [Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Dataset](https://mlsanity.com/paper/2407.13896/) (2024)
- [Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning](https://mlsanity.com/paper/2509.00745/) (2025)
- [Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images](https://mlsanity.com/paper/2504.01838/) (2025)
- [FairLRF: Achieving Fairness through Sparse Low Rank Factorization](https://mlsanity.com/paper/2511.16549/) (2025)
- [Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space](https://mlsanity.com/paper/2402.13061/) (2024)
- [Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis](https://mlsanity.com/paper/2510.16887/) (2025)
- [Mitigating Individual Skin Tone Bias in Skin Lesion Classification through Distribution-Aware Reweighting](https://mlsanity.com/paper/2512.08733/) (2025)
- [FairCompressAgent: An Agentic Framework for Fairness-Aware Model Compression for FPGA Deployment](https://mlsanity.com/paper/2609.17786/) (2026)
- [Is invariance all you need for algorithmic fairness? Removing demographic information can create new bias](https://mlsanity.com/paper/2609.32004/) (2026)

## Abstract (arXiv)

Fairness has become increasingly pivotal in medical image recognition. However, without mitigating bias, deploying unfair medical AI systems could harm the interests of underprivileged populations. In this paper, we observe that while features extracted from the deeper layers of neural networks generally offer higher accuracy, fairness conditions deteriorate as we extract features from deeper layers. This phenomenon motivates us to extend the concept of multi-exit frameworks. Unlike existing works mainly focusing on accuracy, our multi-exit framework is fairness-oriented; the internal classifiers are trained to be more accurate and fairer, with high extensibility to apply to most existing fairness-aware frameworks. During inference, any instance with high confidence from an internal classifier is allowed to exit early. Experimental results show that the proposed framework can improve the fairness condition over the state-of-the-art in two dermatological disease datasets.