# Learning to Cluster Faces via Confidence and Connectivity Estimation

arXiv: https://arxiv.org/abs/2004.00445 · HTML: https://mlsanity.com/paper/2004.00445/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 30 of 42)

- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (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)
- [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)
- [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)
- [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)
- [Learning to Cluster Faces via Transformer](https://mlsanity.com/paper/2104.11502/) (2021)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [MetaAge: Meta-Learning Personalized Age Estimators](https://mlsanity.com/paper/2207.05288/) (2022)
- [FaceMap: Towards Unsupervised Face Clustering via Map Equation](https://mlsanity.com/paper/2203.10090/) (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)
- [Efficient Large-Scale Face Clustering Using an Online Mixture of Gaussians](https://mlsanity.com/paper/2103.17272/) (2021)
- [Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification](https://mlsanity.com/paper/2206.06607/) (2022)
- [Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities](https://mlsanity.com/paper/2308.00588/) (2023)
- [Image Clustering using Restricted Boltzman Machine](https://mlsanity.com/paper/2312.13845/) (2023)
- [URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering](https://mlsanity.com/paper/2407.09120/) (2024)
- [An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better?](https://mlsanity.com/paper/2211.05183/) (2022)
- [A Survey of Face Recognition](https://mlsanity.com/paper/2212.13038/) (2022)

## Abstract (arXiv)

Face clustering is an essential tool for exploiting the unlabeled face data, and has a wide range of applications including face annotation and retrieval. Recent works show that supervised clustering can result in noticeable performance gain. However, they usually involve heuristic steps and require numerous overlapped subgraphs, severely restricting their accuracy and efficiency. In this paper, we propose a fully learnable clustering framework without requiring a large number of overlapped subgraphs. Instead, we transform the clustering problem into two sub-problems. Specifically, two graph convolutional networks, named GCN-V and GCN-E, are designed to estimate the confidence of vertices and the connectivity of edges, respectively. With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters. Experiments on two large-scale benchmarks show that our method significantly improves clustering accuracy and thus performance of the recognition models trained on top, yet it is an order of magnitude more efficient than existing supervised methods.