On mitigating hard clusters for face clustering
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...
Saved in:
Main Authors: | , , , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7512 https://ink.library.smu.edu.sg/context/sis_research/article/8515/viewcontent/ECCV2022_FaceClustering.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-8515 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-85152023-08-04T02:22:56Z On mitigating hard clusters for face clustering CHEN, Yingjie ZHONG, Huasong CHEN, Chong SHEN, Chen HUANG, Jianqiang WANG, Tao LIANG, Yun Qianru SUN, 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. 2022-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7512 info:doi/10.1007/978-3-031-19775-8_31 https://ink.library.smu.edu.sg/context/sis_research/article/8515/viewcontent/ECCV2022_FaceClustering.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University face clustering unsupervised learning density estimation Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
face clustering unsupervised learning density estimation Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
face clustering unsupervised learning density estimation Databases and Information Systems Graphics and Human Computer Interfaces CHEN, Yingjie ZHONG, Huasong CHEN, Chong SHEN, Chen HUANG, Jianqiang WANG, Tao LIANG, Yun Qianru SUN, On mitigating hard clusters for face clustering |
description |
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. |
format |
text |
author |
CHEN, Yingjie ZHONG, Huasong CHEN, Chong SHEN, Chen HUANG, Jianqiang WANG, Tao LIANG, Yun Qianru SUN, |
author_facet |
CHEN, Yingjie ZHONG, Huasong CHEN, Chong SHEN, Chen HUANG, Jianqiang WANG, Tao LIANG, Yun Qianru SUN, |
author_sort |
CHEN, Yingjie |
title |
On mitigating hard clusters for face clustering |
title_short |
On mitigating hard clusters for face clustering |
title_full |
On mitigating hard clusters for face clustering |
title_fullStr |
On mitigating hard clusters for face clustering |
title_full_unstemmed |
On mitigating hard clusters for face clustering |
title_sort |
on mitigating hard clusters for face clustering |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2022 |
url |
https://ink.library.smu.edu.sg/sis_research/7512 https://ink.library.smu.edu.sg/context/sis_research/article/8515/viewcontent/ECCV2022_FaceClustering.pdf |
_version_ |
1773551433538338816 |