Sparse Graph Convolutional Networks for Face Recognition

研究成果: Conference contribution

抄録

In recent years, deep learning networks have substantially improved the performance of face recognition. Although deep learning networks have been very successful, there are limited to underlying Euclidean structure data. When dealing with complex signals such as medical imaging, genetics, social networks and computer vision, recently there has been a growing interest in trying to apply learning on non-Euclidean geometric data. Graph convolutional networks are a new deep learning architecture for analyzing non-Euclidean geometric data. In computer vision, a human face image is modeled as a graph in the irregular domain. A major technical challenge is how to optimize the structured face graph. Because, classification performance critically depends on the quality of the graph. In this paper, we explore an undirected graph convolutional network called SGCNs (k^{3} - sparse graph convolutional networks). The main idea is to use sparsity-constrained optimization that obtain connected sparse subgraphs. A sparse graph of face image is composed of connected sparse subgraphs. Experiments demonstrate that the learned sparse graph has better performance than mutual k-nearest neighbor graph and l1 graph.

本文言語English
ホスト出版物のタイトル2018 15th International Conference on Control, Automation, Robotics and Vision, ICARCV 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ174-179
ページ数6
ISBN(電子版)9781538695821
DOI
出版ステータスPublished - 2018 12 18
イベント15th International Conference on Control, Automation, Robotics and Vision, ICARCV 2018 - Singapore, Singapore
継続期間: 2018 11 182018 11 21

出版物シリーズ

名前2018 15th International Conference on Control, Automation, Robotics and Vision, ICARCV 2018

Other

Other15th International Conference on Control, Automation, Robotics and Vision, ICARCV 2018
国/地域Singapore
CitySingapore
Period18/11/1818/11/21

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ビジョンおよびパターン認識
  • 制御と最適化

フィンガープリント

「Sparse Graph Convolutional Networks for Face Recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル