# How to Boost Face Recognition with StyleGAN?

arXiv: https://arxiv.org/abs/2210.10090 · HTML: https://mlsanity.com/paper/2210.10090/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 70 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 48)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics](https://mlsanity.com/paper/1909.12962/) (2019)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing](https://mlsanity.com/paper/2111.15666/) (2021)
- [Probabilistic Face Embeddings](https://mlsanity.com/paper/1904.09658/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [Towards Measuring Fairness in AI: the Casual Conversations Dataset](https://mlsanity.com/paper/2104.02821/) (2021)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)

## Built on by (most cited first, 10 of 10)

- [TriPlaneNet: An Encoder for EG3D Inversion](https://mlsanity.com/paper/2303.13497/) (2023)
- [Face Generation and Editing with StyleGAN: A Survey](https://mlsanity.com/paper/2212.09102/) (2022)
- [LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition](https://mlsanity.com/paper/2403.08161/) (2024)
- [SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data](https://mlsanity.com/paper/2308.14852/) (2023)
- [Zero-shot racially balanced dataset generation using an existing biased StyleGAN2](https://mlsanity.com/paper/2305.07710/) (2023)
- [AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition](https://mlsanity.com/paper/2503.11544/) (2025)
- [QCFace: Image Quality Control for boosting Face Representation & Recognition](https://mlsanity.com/paper/2510.15289/) (2025)
- [ScoreMix: Synthetic Data Generation by Score Composition in Diffusion Models Improves Recognition](https://mlsanity.com/paper/2506.10226/) (2025)
- [From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images](https://mlsanity.com/paper/2609.02640/) (2026)
- [DenseFace: Bias Mitigation in Face Recognition via Density-Aware Probabilistic Matching](https://mlsanity.com/paper/2609.16149/) (2026)

## Abstract (arXiv)

State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as limited numbers of identities. On the other hand, self-supervised revolution in the industry motivates research on the adaptation of related techniques to facial recognition. One of the most popular practical tricks is to augment the dataset by the samples drawn from generative models while preserving the identity. We show that a simple approach based on fine-tuning pSp encoder for StyleGAN allows us to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities. We also collect large-scale unlabeled datasets with controllable ethnic constitution -- AfricanFaceSet-5M (5 million images of different people) and AsianFaceSet-3M (3 million images of different people) -- and we show that pretraining on each of them improves recognition of the respective ethnicities (as well as others), while combining all unlabeled datasets results in the biggest performance increase. Our self-supervised strategy is the most useful with limited amounts of labeled training data, which can be beneficial for more tailored face recognition tasks and when facing privacy concerns. Evaluation is based on a standard RFW dataset and a new large-scale RB-WebFace benchmark. The code and data are made publicly available at https://github.com/seva100/stylegan-for-facerec.