# Learning to Cluster Faces on an Affinity Graph

arXiv: https://arxiv.org/abs/1904.02749 · HTML: https://mlsanity.com/paper/1904.02749/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 50)

- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [Learning a Proposal Classifier for Multiple Object Tracking](https://mlsanity.com/paper/2103.07889/) (2021)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes](https://mlsanity.com/paper/2103.13225/) (2021)
- [Centroid Transformers: Learning to Abstract with Attention](https://mlsanity.com/paper/2102.08606/) (2021)
- [Learning Hierarchical Graph Neural Networks for Image Clustering](https://mlsanity.com/paper/2107.01319/) (2021)
- [Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.12585/) (2021)
- [Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space](https://mlsanity.com/paper/2202.03800/) (2022)
- [Quantum Vision Clustering](https://mlsanity.com/paper/2309.09907/) (2023)
- [FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding](https://mlsanity.com/paper/2311.15965/) (2023)
- [QClusformer: A Quantum Transformer-based Framework for Unsupervised Visual Clustering](https://mlsanity.com/paper/2405.19722/) (2024)
- [Fairness in Visual Clustering: A Novel Transformer Clustering Approach](https://mlsanity.com/paper/2304.07408/) (2023)
- [Quantum Visual Feature Encoding Revisited](https://mlsanity.com/paper/2405.19725/) (2024)
- [Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis](https://mlsanity.com/paper/2211.06719/) (2022)
- [Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering](https://mlsanity.com/paper/2309.00528/) (2023)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)
- [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)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [Learning to Cluster Faces via Transformer](https://mlsanity.com/paper/2104.11502/) (2021)
- [Globally Correlation-Aware Hard Negative Generation](https://mlsanity.com/paper/2411.13145/) (2024)
- [Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches](https://mlsanity.com/paper/2212.10207/) (2022)
- [Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis](https://mlsanity.com/paper/2507.06689/) (2025)
- [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)
- [Robust Graph Structure Learning via Multiple Statistical Tests](https://mlsanity.com/paper/2210.03956/) (2022)
- [Inter-class Discrepancy Alignment for Face Recognition](https://mlsanity.com/paper/2103.01559/) (2021)

## Abstract (arXiv)

Face recognition sees remarkable progress in recent years, and its performance has reached a very high level. Taking it to a next level requires substantially larger data, which would involve prohibitive annotation cost. Hence, exploiting unlabeled data becomes an appealing alternative. Recent works have shown that clustering unlabeled faces is a promising approach, often leading to notable performance gains. Yet, how to effectively cluster, especially on a large-scale (i.e. million-level or above) dataset, remains an open question. A key challenge lies in the complex variations of cluster patterns, which make it difficult for conventional clustering methods to meet the needed accuracy. This work explores a novel approach, namely, learning to cluster instead of relying on hand-crafted criteria. Specifically, we propose a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters. Experiments show that our method yields significantly more accurate face clusters, which, as a result, also lead to further performance gain in face recognition.