On Mitigating Hard Clusters for Face Clustering

TL;DR

This paper proposes a novel approach to improve face clustering by addressing hard clusters through neighborhood-based probabilistic inference, enhancing existing methods to achieve state-of-the-art results.

Contribution

Introduction of two modules, NDDe and TPDi, that leverage neighborhood information to better identify hard clusters in face clustering tasks.

Findings

Modules improve clustering accuracy on benchmarks.

Combining modules with existing methods boosts performance.

Achieves new state-of-the-art results in face clustering.

Abstract

Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, \ie, high variations in size and sparsity, of the clusters. Consequently, the conventional way of using a uniform threshold (to identify clusters) often leads to a terrible misclassification for the samples that should belong to hard clusters. We tackle this problem by leveraging the neighborhood information of samples and inferring the cluster memberships (of samples) in a probabilistic way. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi), based on which we can simply apply the standard Density Peak Clustering algorithm with a uniform threshold. Our experiments on multiple benchmarks show that each module contributes to the final performance of our method, and by incorporating them into other advanced face clustering methods, these two modules can boost the performance of these methods to a new state-of-the-art. Code is available at: https://github.com/echoanran/On-Mitigating-Hard-Clusters.