Hybrid Deep Learning for Face Verification
Publication in refereed journal


香港中文大学研究人员 ( 现职)

汤晓鸥教授 (信息工程学系)

王晓刚教授 (电子工程学系)

全文

数位物件识别号 (DOI) http://dx.doi.org/10.1109/TPAMI.2015.2505293

引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/1WOS source URL

其它资讯

摘要This paper proposes a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for face verification. A key contribution of this work is to learn high-level relational visual features with rich identity similarity information. The deep ConvNets in our model start by extracting local relational visual features from two face images in comparison, which are further processed through multiple layers to extract high-level and global relational features. To keep enough discriminative information, we use the last hidden layer neuron activations of the ConvNet as features for face verification instead of those of the output layer. To characterize face similarities from different aspects, we concatenate the features extracted from different face region pairs by different deep ConvNets. The resulting high-dimensional relational features are classified by an RBM for face verification. After pre-training each ConvNet and the RBM separately, the entire hybrid network is jointly optimized to further improve the accuracy. Various aspects of the ConvNet structures, relational features, and face verification classifiers are investigated. Our model achieves the state-of-the-art face verification performance on the challenging LFW dataset under both the unrestricted protocol and the setting when outside data is allowed to be used for training.

着者Sun Y, Wang XG, Tang XO
期刊名称IEEE Transactions on Pattern Analysis and Machine Intelligence,IEEE Transactions on Pattern Analysis and Machine Intelligence
出版年份20http://aims.cuhk.edu.hk/converis/portal/Publication/16
月份http://aims.cuhk.edu.hk/converis/portal/Publication/10
日期http://aims.cuhk.edu.hk/converis/portal/Publication/1
卷号38
期次http://aims.cuhk.edu.hk/converis/portal/Publication/10
出版社IEEE COMPUTER SOC
页次http://aims.cuhk.edu.hk/converis/portal/Publication/1997 - 2009
国际标準期刊号0http://aims.cuhk.edu.hk/converis/portal/Publication/162-8828
电子国际标準期刊号http://aims.cuhk.edu.hk/converis/portal/Publication/1939-3539
语言英式英语

关键词Convolutional networks; deep learning; face recognition
Web of Science 学科类别Computer Science; Computer Science, Artificial Intelligence; Engineering; Engineering, Electrical & Electronic