Semi-supervised elastic manifold embedding with deep learning architecture
作者：
Highlights：
• The letter introduces a novel deep architecture for manifold learning.
• It provides a deep non-linear embedded data together with a linear model.
• It is composed of layers that integrate sparse graphs and elastic manifold embedding.
• The proposed framework can be used by both settings: supervised and semi-supervised.
• Performance is studied and compared using several public image databases.
摘要
•The letter introduces a novel deep architecture for manifold learning.•It provides a deep non-linear embedded data together with a linear model.•It is composed of layers that integrate sparse graphs and elastic manifold embedding.•The proposed framework can be used by both settings: supervised and semi-supervised.•Performance is studied and compared using several public image databases.
论文关键词：Graph-based embedding,Elastic embedding,Deep learning architecture,Supervised learning,Semi-supervised learning
论文评审过程：Received 8 July 2019, Revised 18 December 2019, Accepted 5 May 2020, Available online 30 May 2020, Version of Record 9 June 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107425
