Face Clustering: Representation and Pairwise Constraints

06/15/2017
by   Yichun Shi, et al.
0

Clustering face images according to their identity has two important applications: (i) grouping a collection of face images when no external labels are associated with images, and (ii) indexing for efficient large scale face retrieval. The clustering problem is composed of two key parts: face representation and choice of similarity for grouping faces. We first propose a representation based on ResNet, which has been shown to perform very well in image classification problems. Given this representation, we design a clustering algorithm, Conditional Pairwise Clustering (ConPaC), which directly estimates the adjacency matrix only based on the similarity between face images. This allows a dynamic selection of number of clusters and retains pairwise similarity between faces. ConPaC formulates the clustering problem as a Conditional Random Field (CRF) model and uses Loopy Belief Propagation to find an approximate solution for maximizing the posterior probability of the adjacency matrix. Experimental results on two benchmark face datasets (LFW and IJB-B) show that ConPaC outperforms well known clustering algorithms such as k-means, spectral clustering and approximate rank-order. Additionally, our algorithm can naturally incorporate pairwise constraints to obtain a semi-supervised version that leads to improved clustering performance. We also propose an k-NN variant of ConPaC, which has a linear time complexity given a k-NN graph, suitable for large datasets.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 10

research
04/04/2016

Clustering Millions of Faces by Identity

In this work, we attempt to address the following problem: Given a large...
research
07/13/2017

Merge or Not? Learning to Group Faces via Imitation Learning

Given a large number of unlabeled face images, face grouping aims at clu...
research
03/14/2017

A Proximity-Aware Hierarchical Clustering of Faces

In this paper, we propose an unsupervised face clustering algorithm call...
research
07/11/2021

Similarity Guided Deep Face Image Retrieval

Face image retrieval, which searches for images of the same identity fro...
research
05/26/2022

Learn to Cluster Faces via Pairwise Classification

Face clustering plays an essential role in exploiting massive unlabeled ...
research
02/05/2019

Adjacency-constrained hierarchical clustering of a band similarity matrix with application to Genomics

Motivation: Genomic data analyses such as Genome-Wide Association Studie...
research
03/24/2021

Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes

Face clustering is a promising method for annotating unlabeled face imag...

Please sign up or login with your details

Forgot password? Click here to reset