# Hairmony: Fairness-aware hairstyle classification

arXiv: https://arxiv.org/abs/2410.11528 · HTML: https://mlsanity.com/paper/2410.11528/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age](https://mlsanity.com/paper/1908.04913/) (2019)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (2023)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling](https://mlsanity.com/paper/2303.02700/) (2023)
- [HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles](https://mlsanity.com/paper/2312.11666/) (2023)
- [GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations](https://mlsanity.com/paper/2311.02062/) (2023)
- [K-Hairstyle: A Large-scale Korean Hairstyle Dataset for Virtual Hair Editing and Hairstyle Classification](https://mlsanity.com/paper/2102.06288/) (2021)
- [Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning](https://mlsanity.com/paper/2302.11102/) (2023)
- [Countering Racial Bias in Computer Graphics Research](https://mlsanity.com/paper/2103.15163/) (2021)
- [Sex and Gender in the Computer Graphics Research Literature](https://mlsanity.com/paper/2206.00480/) (2022)
- [CelebHair: A New Large-Scale Dataset for Hairstyle Recommendation based on CelebA](https://mlsanity.com/paper/2104.06885/) (2021)

## Built on by (most cited first, 5 of 5)

- [Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars](https://mlsanity.com/paper/2509.01469/) (2025)
- [StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors](https://mlsanity.com/paper/2412.11586/) (2024)
- [HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis](https://mlsanity.com/paper/2605.08824/) (2026)
- [HairLRM: Strand-based Hair Modeling via Large Reconstruction Models](https://mlsanity.com/paper/2606.15238/) (2026)
- [Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands](https://mlsanity.com/paper/2607.09811/) (2026)

## Abstract (arXiv)

We present a method for prediction of a person's hairstyle from a single image. Despite growing use cases in user digitization and enrollment for virtual experiences, available methods are limited, particularly in the range of hairstyles they can capture. Human hair is extremely diverse and lacks any universally accepted description or categorization, making this a challenging task. Most current methods rely on parametric models of hair at a strand level. These approaches, while very promising, are not yet able to represent short, frizzy, coily hair and gathered hairstyles. We instead choose a classification approach which can represent the diversity of hairstyles required for a truly robust and inclusive system. Previous classification approaches have been restricted by poorly labeled data that lacks diversity, imposing constraints on the usefulness of any resulting enrollment system. We use only synthetic data to train our models. This allows for explicit control of diversity of hairstyle attributes, hair colors, facial appearance, poses, environments and other parameters. It also produces noise-free ground-truth labels. We introduce a novel hairstyle taxonomy developed in collaboration with a diverse group of domain experts which we use to balance our training data, supervise our model, and directly measure fairness. We annotate our synthetic training data and a real evaluation dataset using this taxonomy and release both to enable comparison of future hairstyle prediction approaches. We employ an architecture based on a pre-trained feature extraction network in order to improve generalization of our method to real data and predict taxonomy attributes as an auxiliary task to improve accuracy. Results show our method to be significantly more robust for challenging hairstyles than recent parametric approaches.