# Clustering Millions of Faces by Identity

arXiv: https://arxiv.org/abs/1604.00989 · HTML: https://mlsanity.com/paper/1604.00989/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2016.

## Built on by (most cited first, 26 of 26)

- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [Perspectives on individual animal identification from biology and computer vision](https://mlsanity.com/paper/2103.00560/) (2021)
- [Face, Body, Voice: Video Person-Clustering with Multiple Modalities](https://mlsanity.com/paper/2105.09939/) (2021)
- [Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes](https://mlsanity.com/paper/2103.13225/) (2021)
- [Learning Hierarchical Graph Neural Networks for Image Clustering](https://mlsanity.com/paper/2107.01319/) (2021)
- [Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification](https://mlsanity.com/paper/2104.02265/) (2021)
- [QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering](https://mlsanity.com/paper/2405.19722/) (2024)
- [Quantum Visual Feature Encoding Revisited](https://mlsanity.com/paper/2405.19725/) (2024)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)
- [On Mitigating Hard Clusters for Face Clustering](https://mlsanity.com/paper/2207.11895/) (2022)
- [Learning to Cluster Faces via Transformer](https://mlsanity.com/paper/2104.11502/) (2021)
- [FaceMap: Towards Unsupervised Face Clustering via Map Equation](https://mlsanity.com/paper/2203.10090/) (2022)
- [Self-supervised Video-centralised Transformer for Video Face Clustering](https://mlsanity.com/paper/2203.13166/) (2022)
- [Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians](https://mlsanity.com/paper/2103.17272/) (2021)
- [Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities](https://mlsanity.com/paper/2308.00588/) (2023)
- [An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?](https://mlsanity.com/paper/2211.05183/) (2022)
- [Face Clustering via Early Stopping and Edge Recall](https://mlsanity.com/paper/2408.13431/) (2024)
- [Chaotic-to-Fine Clustering for Unlabeled Plant Disease Images](https://mlsanity.com/paper/2101.06820/) (2021)
- [Fitting large mixture models using stochastic component selection](https://mlsanity.com/paper/2110.04776/) (2021)
- [Density-Based Clustering with Kernel Diffusion](https://mlsanity.com/paper/2110.05096/) (2021)
- [FCM-DNN: diagnosing coronary artery disease by deep accuracy Fuzzy C-Means clustering model](https://mlsanity.com/paper/2202.04645/) (2022)
- [Face Clustering for Connection Discovery from Event Images](https://mlsanity.com/paper/2309.01092/) (2023)
- [Cross-Camera Data Association via GNN for Supervised Graph Clustering](https://mlsanity.com/paper/2410.00643/) (2024)
- [A Greedy Strategy for Graph Cut](https://mlsanity.com/paper/2412.20035/) (2024)

## Abstract (arXiv)

In this work, we attempt to address the following problem: Given a large number of unlabeled face images, cluster them into the individual identities present in this data. We consider this a relevant problem in different application scenarios ranging from social media to law enforcement. In large-scale scenarios the number of faces in the collection can be of the order of hundreds of million, while the number of clusters can range from a few thousand to millions--leading to difficulties in terms of both run-time complexity and evaluating clustering and per-cluster quality. An efficient and effective Rank-Order clustering algorithm is developed to achieve the desired scalability, and better clustering accuracy than other well-known algorithms such as k-means and spectral clustering. We cluster up to 123 million face images into over 10 million clusters, and analyze the results in terms of both external cluster quality measures (known face labels) and internal cluster quality measures (unknown face labels) and run-time. Our algorithm achieves an F-measure of 0.87 on a benchmark unconstrained face dataset (LFW, consisting of 13K faces), and 0.27 on the largest dataset considered (13K images in LFW, plus 123M distractor images). Additionally, we present preliminary work on video frame clustering (achieving 0.71 F-measure when clustering all frames in the benchmark YouTube Faces dataset). A per-cluster quality measure is developed which can be used to rank individual clusters and to automatically identify a subset of good quality clusters for manual exploration.