# Level Playing Field for Million Scale Face Recognition

arXiv: https://arxiv.org/abs/1705.00393 · HTML: https://mlsanity.com/paper/1705.00393/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 30 of 43)

- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [DigiFace-1M: 1 Million Digital Face Images for Face Recognition](https://mlsanity.com/paper/2210.02579/) (2022)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Masked Face Recognition Challenge: The InsightFace Track Report](https://mlsanity.com/paper/2108.08191/) (2021)
- [Synthetic Data for Face Recognition: Current State and Future Prospects](https://mlsanity.com/paper/2305.01021/) (2023)
- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [OPOM: Customized Invisible Cloak towards Face Privacy Protection](https://mlsanity.com/paper/2205.11981/) (2022)
- [SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition](https://mlsanity.com/paper/2205.12010/) (2022)
- [Dynamic Class Queue for Large Scale Face Recognition In the Wild](https://mlsanity.com/paper/2105.11113/) (2021)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Masked Face Recognition Challenge: The WebFace260M Track Report](https://mlsanity.com/paper/2108.07189/) (2021)
- [CapsField: Light Field-based Face and Expression Recognition in the Wild using Capsule Routing](https://mlsanity.com/paper/2101.03503/) (2021)
- [What's in a Decade? Transforming Faces Through Time](https://mlsanity.com/paper/2210.06642/) (2022)
- [Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise](https://mlsanity.com/paper/2510.17372/) (2025)
- [FaceMAE: Privacy-Preserving Face Recognition via Masked Autoencoders](https://mlsanity.com/paper/2205.11090/) (2022)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)
- [EFHQ: Multi-purpose ExtremePose-Face-HQ dataset](https://mlsanity.com/paper/2312.17205/) (2023)
- [AdvCloak: Customized Adversarial Cloak for Privacy Protection](https://mlsanity.com/paper/2312.14407/) (2023)
- [VIGFace: Virtual Identity Generation for Privacy-Free Face Recognition](https://mlsanity.com/paper/2403.08277/) (2024)
- [ADD: An Automatic Desensitization Fisheye Dataset for Autonomous Driving](https://mlsanity.com/paper/2308.07590/) (2023)
- [From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning](https://mlsanity.com/paper/2501.01760/) (2025)
- [The Cultivated Practices of Text-to-Image Generation](https://mlsanity.com/paper/2306.11393/) (2023)
- [ProS: Facial Omni-Representation Learning via Prototype-based Self-Distillation](https://mlsanity.com/paper/2311.01929/) (2023)
- [Deep Image Retrieval is not Robust to Label Noise](https://mlsanity.com/paper/2205.11195/) (2022)
- [Learning Domain and Pose Invariance for Thermal-to-Visible Face Recognition](https://mlsanity.com/paper/2211.09350/) (2022)
- [Cross-Age Contrastive Learning for Age-Invariant Face Recognition](https://mlsanity.com/paper/2312.11195/) (2023)
- [Massively Annotated Datasets for Assessment of Synthetic and Real Data in Face Recognition](https://mlsanity.com/paper/2404.15234/) (2024)
- [GIF: Generative Inspiration for Face Recognition at Scale](https://mlsanity.com/paper/2505.03012/) (2025)
- [Restoring Gaussian Blurred Face Images for Deanonymization Attacks](https://mlsanity.com/paper/2506.12344/) (2025)
- [Object Recognition Datasets and Challenges: A Review](https://mlsanity.com/paper/2507.22361/) (2025)

## Abstract (arXiv)

Face recognition has the perception of a solved problem, however when tested at the million-scale exhibits dramatic variation in accuracies across the different algorithms. Are the algorithms very different? Is access to good/big training data their secret weapon? Where should face recognition improve? To address those questions, we created a benchmark, MF2, that requires all algorithms to be trained on same data, and tested at the million scale. MF2 is a public large-scale set with 672K identities and 4.7M photos created with the goal to level playing field for large scale face recognition. We contrast our results with findings from the other two large-scale benchmarks MegaFace Challenge and MS-Celebs-1M where groups were allowed to train on any private/public/big/small set. Some key discoveries: 1) algorithms, trained on MF2, were able to achieve state of the art and comparable results to algorithms trained on massive private sets, 2) some outperformed themselves once trained on MF2, 3) invariance to aging suffers from low accuracies as in MegaFace, identifying the need for larger age variations possibly within identities or adjustment of algorithms in future testings.