Multi-label learning based deep transfer neural network for facial attribute classification
作者：
Highlights：
• A deep transfer neural network, FMTNet, is proposed for facial attribute analysis.
• FMTNet effectively performs deep transfer learning based on multi-label learning.
• FMTNet has three sub-networks carefully designed in a similar network structure.
• An effective loss weight scheme is developed based on attribute grouping.
• Experiments on facial attribute analysis show the effectiveness of our method.
摘要
•A deep transfer neural network, FMTNet, is proposed for facial attribute analysis.•FMTNet effectively performs deep transfer learning based on multi-label learning.•FMTNet has three sub-networks carefully designed in a similar network structure.•An effective loss weight scheme is developed based on attribute grouping.•Experiments on facial attribute analysis show the effectiveness of our method.
论文关键词：Transfer learning,Facial attribute classification,Multi-label learning,Deep learning,Convolutional neural networks
论文评审过程：Received 30 June 2017, Revised 10 February 2018, Accepted 20 March 2018, Available online 21 March 2018, Version of Record 30 March 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.03.018
