Deep Network Shrinkage Applied To Cross-Spectrum Face Recognition
2017 12TH IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG 2017)(2017)
摘要
In recent years, deep learning has emerged as a dominant methodology in virtually all machine learning problems. While it has been shown to produce state-of-the-art results for a variety of applicatons (including face recognition and heterogeneous face recognition), one aspect of deep networks that has not been extensively researched is how to determine the optimal network structure. This problem is generally solved by ad hoc methods. In this work we address a subproblem of this task: determining the breadth (number of nodes) of each layer. We show how to use group-sparsity-inducing regularization to effectively replace these hyper-parameters with a single hyper-parameter which can be determined by cross-validation. We demonstrate our method by using it to reduce the size of networks on two commonly used NIR face datasets.
更多查看译文
关键词
deep network shrinkage,cross-spectrum face recognition,deep learning,machine learning,heterogeneous face recognition,deep networks,optimal network structure,group-sparsity-inducing regularization,cross-validation,network size reduction,NIR face datasets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络