Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2022

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, i.e., 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.

Keywords

face clustering, unsupervised learning, density estimation

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Data Science and Engineering

Publication

Computer Vision: ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27: Proceedings

Volume

13672

First Page

529

Last Page

544

ISBN

9783031198052

Identifier

10.1007/978-3-031-19775-8_31

Publisher

Springer

City or Country

Cham

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1007/978-3-031-19775-8_31

Download

Share

COinS