Generic Sparse Graph Based Convolutional Networks for Face Recognition
Generic Sparse Graph Based Convolutional Networks for Face Recognition
复制标题
DOI：
10.1109/icip42928.2021.9506083
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
R. Wu;S. Kamata
中科院分区：
文献类型：
--
作者：
R. Wu;S. Kamata
已经提出了几种基于图的方法来执行人脸识别，例如弹性图匹配等。这些方法利用了人脸具有图结构的事实。然而，这些方法比CNN弱。随着图卷积神经网络（GCNN）的发展，我们可以重新考虑识别图结构的好处。在本文中，人脸图像被建模为稀疏图。主要的挑战是如何估计稀疏图。通常，稀疏图是基于一些先前的聚类方法，如k-nn等，这将导致学习的图更接近先前的图。另一个问题是正则化参数难以准确估计。本文提出了一种通用的基于稀疏图的卷积网络（GSgCN）。我们有三个优势：1）在一般稀疏图建模中不估计正则化参数，2）非先验，以及3）每个稀疏子图被表示为最相邻相关顶点的连通图。由于一般稀疏图表示是非凸的，我们实现了投影梯度下降算法与结构化稀疏表示。实验结果表明，GSgCN具有良好的性能相比，一些国家的最先进的方法。
Several graph-based methods have been proposed to perform face recognition, such as elastic graph matching, etc. These methods take advantage of the fact that the face has a graph structure. However, these methods are weaker than the CNNs. With the development of graph convolutional neural networks (GCNNs), we can reconsider the benefits of identifying the graph structure. In this paper, a face image is modeled as a sparse graph. The major challenge is how to estimate the sparse graph. Usually, the sparse graph is based on some prior clustering methods, such as k-nn, etc., that will cause the learned graph to be closer to the prior graph. Another problem is that the regularization parameters are difficult to accurately estimate. This paper presents a generic sparse graph based convolutional networks (GSgCNs). We have three advantages: 1) the regularization parameters are not estimated in the generic sparse graph modeling, 2) non-prior and 3) each sparse subgraph is represented as a connected graph of the most adjacent-relevant vertices. Because the generic sparse graph representation is non-convex, we implement the projected gradient descent algorithm with structured sparse representation. Experimental results demonstrate that the GSgCNs have good performance compared with some state-of-the-art methods.