# A Proximity-Aware Hierarchical Clustering of Faces

## TL;DR

This paper introduces an unsupervised face clustering method called Proximity-Aware Hierarchical Clustering that leverages local deep feature structures and SVM-based similarity measures to improve clustering accuracy on challenging datasets.

## Contribution

The paper presents a novel unsupervised clustering algorithm that uses local deep features and SVM margins, requiring no external training data, and demonstrates its effectiveness on multiple face datasets.

## Key findings

- Achieves significant improvements over state-of-the-art methods.
- Effectively curates large-scale noisy datasets for training.
- Enhances face verification performance through dataset fine-tuning.

## Abstract

In this paper, we propose an unsupervised face clustering algorithm called "Proximity-Aware Hierarchical Clustering" (PAHC) that exploits the local structure of deep representations. In the proposed method, a similarity measure between deep features is computed by evaluating linear SVM margins. SVMs are trained using nearest neighbors of sample data, and thus do not require any external training data. Clusters are then formed by thresholding the similarity scores. We evaluate the clustering performance using three challenging unconstrained face datasets, including Celebrity in Frontal-Profile (CFP), IARPA JANUS Benchmark A (IJB-A), and JANUS Challenge Set 3 (JANUS CS3) datasets. Experimental results demonstrate that the proposed approach can achieve significant improvements over state-of-the-art methods. Moreover, we also show that the proposed clustering algorithm can be applied to curate a set of large-scale and noisy training dataset while maintaining sufficient amount of images and their variations due to nuisance factors. The face verification performance on JANUS CS3 improves significantly by finetuning a DCNN model with the curated MS-Celeb-1M dataset which contains over three million face images.