FaceMap: Towards Unsupervised Face Clustering via Map Equation

03/21/2022
by   Xiaotian Yu, et al.
0

Face clustering is an essential task in computer vision due to the explosion of related applications such as augmented reality or photo album management. The main challenge of this task lies in the imperfectness of similarities among image feature representations. Given an existing feature extraction model, it is still an unresolved problem that how can the inherent characteristics of similarities of unlabelled images be leveraged to improve the clustering performance. Motivated by answering the question, we develop an effective unsupervised method, named as FaceMap, by formulating face clustering as a process of non-overlapping community detection, and minimizing the entropy of information flows on a network of images. The entropy is denoted by the map equation and its minimum represents the least description of paths among images in expectation. Inspired by observations on the ranked transition probabilities in the affinity graph constructed from facial images, we develop an outlier detection strategy to adaptively adjust transition probabilities among images. Experiments with ablation studies demonstrate that FaceMap significantly outperforms existing methods and achieves new state-of-the-arts on three popular large-scale datasets for face clustering, e.g., an absolute improvement of more than 10% and 4% comparing with prior unsupervised and supervised methods respectively in terms of average of Pairwise F-score. Our code is publicly available on github.

READ FULL TEXT

page 2

page 4

research
04/23/2021

Learning to Cluster Faces via Transformer

Face clustering is a useful tool for applications like automatic face an...
research
04/05/2020

Clustering based Contrastive Learning for Improving Face Representations

A good clustering algorithm can discover natural groupings in data. Thes...
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...
research
11/12/2018

Variational Community Partition with Novel Network Structure Centrality Prior

In this paper, we proposed a novel two-stage optimization method for net...
research
09/11/2020

SA-Net: A deep spectral analysis network for image clustering

Although supervised deep representation learning has attracted enormous ...
research
08/25/2012

Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

This paper proposes a simple but effective graph-based agglomerative alg...

Please sign up or login with your details

Forgot password? Click here to reset