计算机工程与应用2016，Vol.52Issue(13)：32-37,88,7.DOI:10.3778/j.issn.1002-8331.1601-0367
多任务学习及卷积神经网络在人脸识别中的应用
Multitask learning and CNN for application of face recognition.
摘要
Abstract
With the development of deep learning, face recognition algorithm has made tremendous breakthroughs. How-ever, among current face recognition frameworks, each task(face identification, face verification or attribute classifica-tion)is independently designed and manipulated, which makes the algorithm inefficient and time-consuming. According to the problem, this paper proposes a multi-task convolution deep network. By combining face identification, verification and attribute classification losses as this loss function, the deep convolution network can be trained from end to end and the algorithm will be simple and efficient. This network can complete these three tasks without additional steps. Experi-ments show that the model can still achieve good performance with limited training data and get 97.3% accuracy in the authoritative face recognition dataset LFW(Labeled Face in the Wild).关键词
人脸识别/卷积神经网络/深度学习/多任务学习Key words
face recognition/convolution neural network/deep learning/multitask learning分类
数理科学引用本文复制引用
邵蔚元,郭跃飞..多任务学习及卷积神经网络在人脸识别中的应用[J].计算机工程与应用,2016,52(13):32-37,88,7.基金项目
上海市科委科技创新行动计划(No.14511106900). （No.14511106900）
