人脸聚类-2020 CVPR Learning to Cluster Faces via Confidence and Connectivity Estimation

论文链接

Abstract人脸聚类是挖掘未标记人脸的一个主要方法,在人脸标注和检索等方面有着广泛的应用。最近研究表明,有监督聚类可以显著提高性能。然而,它们通常包含启发式步骤,并且需要大量重叠的子图,这严重限制了准确性和效率。本文提出了一个不需要大量重叠子图的、完全可学习聚类框架。我们将聚类问题转化为两个子问题,具体来说,是两类图卷积网络:GCN-V与GCN-E,GCN-V是用来估计顶点的置信度,GCN-E是用来估计边的连接度。通过顶点的置信度与边的连接度,我们可以自然地组织更多的相关顶点,并将它们组合成簇。在两种大规模数据实验结果表明,该方法显著地提高了聚类精度,从而提高了识别模型的性能,使识别效率较现有的监督方法有较大提升。

Introduction

本文的核心是两个GCN网络,即GCN-V与GCN-E(如下图所示)。

 

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 1
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