cvpr 2019--人脸聚类

本文聚焦于CVPR2019中两篇关于人脸聚类的论文,介绍使用图卷积网络解决人脸聚类挑战的方法,包括不同光照、角度及年龄变化的影响,以及评估聚类效果的F-score和NMI指标。

cvpr 2019 有两篇文章是关于人脸聚类的

1.learning to Cluster Faces on an affinity Graph

链接:https://arxiv.org/pdf/1904.02749.pdf

2. Linkage Based Face Clustering via Graph Convolution Network
https://arxiv.org/pdf/1903.11306.pdf

这两篇都是用Graph Convolution Network 来聚类人脸。

首先我们明确在人脸聚类的问题:

A. 一个人会因为年龄跨度大、角度、光线等情况,(比如一个人自己的正脸与侧脸的相似度的得分其实就比较低)

B. 孤立点,聚类得到的人脸文件夹很多都是一个人脸

孤立点我们用程序去除。--暂时不在我们考虑的范围之内

那么这两篇文章都是为了解决尽量把一个人聚类到一个文件夹下的问题。

人脸聚类的两个评价指标:

F-score 和 NMI 

A.NMI (normalized mutual inofrmation)


B. F-score 的定义

 

 

 

 

 

 

 

 

 

 

Abstract—Clustering face images according to their latent 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: representation and similarity metric for face images, and choice of the partition algorithm. 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 similarities between face images. This allows a dynamic selection of number of clusters and retains pairwise similarities 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 work in a semi-supervised way 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. Index Terms—face clustering, face representation, Conditional Random Fields, pairwise constraints, semi-supervised clustering.
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值