# TrueSkin: Towards Fair and Accurate Skin Tone Recognition and Generation

arXiv: https://arxiv.org/abs/2509.10980 · HTML: https://mlsanity.com/paper/2509.10980/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 13 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [InstantID: Zero-shot Identity-Preserving Generation in Seconds](https://mlsanity.com/paper/2401.07519/) (2024)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [PuLID: Pure and Lightning ID Customization via Contrastive Alignment](https://mlsanity.com/paper/2404.16022/) (2024)
- [Disparities in Dermatology AI: Assessments Using Diverse Clinical Images](https://mlsanity.com/paper/2111.08006/) (2021)
- [TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models](https://mlsanity.com/paper/2312.01261/) (2023)
- [Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm](https://mlsanity.com/paper/2207.02942/) (2022)
- [Consensus and Subjectivity of Skin Tone Annotation for ML Fairness](https://mlsanity.com/paper/2305.09073/) (2023)
- [Crowdsourcing Dermatology Images with Google Search Ads: Creating a Real-World Skin Condition Dataset](https://mlsanity.com/paper/2402.18545/) (2024)
- [Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color](https://mlsanity.com/paper/2309.05148/) (2023)
- [Analysis of Manual and Automated Skin Tone Assignments for Face Recognition Applications](https://mlsanity.com/paper/2104.14685/) (2021)
- [Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets](https://mlsanity.com/paper/2305.09072/) (2023)
- [Can Vision-Language Models Replace Human Annotators: A Case Study with CelebA Dataset](https://mlsanity.com/paper/2410.09416/) (2024)

## Built on by (most cited first, 2 of 2)

- [Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models](https://mlsanity.com/paper/2602.16149/) (2026)
- [Beyond Realism: Learning the Art of Expressive Composition with StickerNet](https://mlsanity.com/paper/2511.20957/) (2025)

## Abstract (arXiv)

Skin tone recognition and generation play important roles in model fairness, healthcare, and generative AI, yet they remain challenging due to the lack of comprehensive datasets and robust methodologies. Compared to other human image analysis tasks, state-of-the-art large multimodal models (LMMs) and image generation models struggle to recognize and synthesize skin tones accurately. To address this, we introduce TrueSkin, a dataset with 7299 images systematically categorized into 6 classes, collected under diverse lighting conditions, camera angles, and capture settings. Using TrueSkin, we benchmark existing recognition and generation approaches, revealing substantial biases: LMMs tend to misclassify intermediate skin tones as lighter ones, whereas generative models struggle to accurately produce specified skin tones when influenced by inherent biases from unrelated attributes in the prompts, such as hairstyle or environmental context. We further demonstrate that training a recognition model on TrueSkin improves classification accuracy by more than 20% compared to LMMs and conventional approaches, and fine-tuning with TrueSkin significantly improves skin tone fidelity in image generation models. Our findings highlight the need for comprehensive datasets like TrueSkin, which not only serves as a benchmark for evaluating existing models but also provides a valuable training resource to enhance fairness and accuracy in skin tone recognition and generation tasks.