Deep adaptive feature enrichment
作者：
Highlights：
• Automatically find optimum coding deep structural modules for enriching raw features.
• Adaptation to the nature of data.
• Independent from complexity of classifier.
• Significantly increasing correct recognition rate for UCI datasets.
• Significantly improve verification and Identification rate for Face Yale database.
摘要
•Automatically find optimum coding deep structural modules for enriching raw features.•Adaptation to the nature of data.•Independent from complexity of classifier.•Significantly increasing correct recognition rate for UCI datasets.•Significantly improve verification and Identification rate for Face Yale database.
论文关键词：Deep learning,Deep features,Feature enrichment,Neural network,Optimization algorithm,Face verification
论文评审过程：Received 23 July 2019, Revised 16 July 2020, Accepted 17 July 2020, Available online 24 July 2020, Version of Record 31 July 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113780
