# Learn to Cluster Faces via Pairwise Classification

arXiv: https://arxiv.org/abs/2205.13117 · HTML: https://mlsanity.com/paper/2205.13117/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 16 of 16)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Linkage Based Face Clustering via Graph Convolution Network](https://mlsanity.com/paper/1903.11306/) (2019)
- [Learning to Cluster Faces on an Affinity Graph](https://mlsanity.com/paper/1904.02749/) (2019)
- [Level Playing Field for Million Scale Face Recognition](https://mlsanity.com/paper/1705.00393/) (2017)
- [Learning to Cluster Faces via Confidence and Connectivity Estimation](https://mlsanity.com/paper/2004.00445/) (2020)
- [Clustering Millions of Faces by Identity](https://mlsanity.com/paper/1604.00989/) (2016)
- [Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition](https://mlsanity.com/paper/1809.01407/) (2018)
- [Accelerated Training for Massive Classification via Dynamic Class Selection](https://mlsanity.com/paper/1801.01687/) (2018)
- [Face Clustering: Representation and Pairwise Constraints](https://mlsanity.com/paper/1706.05067/) (2017)
- [Efficient Large-scale Approximate Nearest Neighbor Search on the GPU](https://mlsanity.com/paper/1702.05911/) (2017)
- [Merge or Not? Learning to Group Faces via Imitation Learning](https://mlsanity.com/paper/1707.03986/) (2017)

## Built on by (most cited first, 7 of 7)

- [Quantum Visual Feature Encoding Revisited](https://mlsanity.com/paper/2405.19725/) (2024)
- [On Mitigating Hard Clusters for Face Clustering](https://mlsanity.com/paper/2207.11895/) (2022)
- [Image Clustering using Restricted Boltzman Machine](https://mlsanity.com/paper/2312.13845/) (2023)
- [On Biased Behavior of GANs for Face Verification](https://mlsanity.com/paper/2208.13061/) (2022)
- [Learn to Cluster Faces with Better Subgraphs](https://mlsanity.com/paper/2304.10831/) (2023)
- [Face Clustering for Connection Discovery from Event Images](https://mlsanity.com/paper/2309.01092/) (2023)
- [Enhancing Noise Resilience in Face Clustering via Sparse Differential Transformer](https://mlsanity.com/paper/2512.22612/) (2025)

## Abstract (arXiv)

Face clustering plays an essential role in exploiting massive unlabeled face data. Recently, graph-based face clustering methods are getting popular for their satisfying performances. However, they usually suffer from excessive memory consumption especially on large-scale graphs, and rely on empirical thresholds to determine the connectivities between samples in inference, which restricts their applications in various real-world scenes. To address such problems, in this paper, we explore face clustering from the pairwise angle. Specifically, we formulate the face clustering task as a pairwise relationship classification task, avoiding the memory-consuming learning on large-scale graphs. The classifier can directly determine the relationship between samples and is enhanced by taking advantage of the contextual information. Moreover, to further facilitate the efficiency of our method, we propose a rank-weighted density to guide the selection of pairs sent to the classifier. Experimental results demonstrate that our method achieves state-of-the-art performances on several public clustering benchmarks at the fastest speed and shows a great advantage in comparison with graph-based clustering methods on memory consumption.