北京交通大学学报2017，Vol.41Issue(6)：27-33,41,8.DOI:10.11860/j.issn.1673-0291.2017.06.005
基于深度特征蒸馏的人脸识别
Face recognition based on deep feature distillation
摘要
Abstract
Deep learning has been widely used in face recognition system due to its powerful ability in feature representation.However,the high inferring complexity and feature representation re-duce the efficiencies in feature extraction and retrieval respectively,which hinders the practical deployments of face recognition system.To address these issues,this paper proposes deep feature distillation in order to uniformly compress the deep network parameters and feature dimensions by distilling the knowledge from large teacher network and domain related data via multi-task deep learning.Combined feature regression and face classification,the method uses a pre-trained large depth network as a teacher network to guide the training of small network,which the knowledge transferred to the lightweight student network to achieve efficient feature extraction. The experimental results on LFW benchmark show that in the condition of the student model rec-ognition accuracy is reduced by 3.7％ compared with the teacher model,the network has been compressed to about 2×107 in model size and 128 dimensional feature,which achieves the reduc-tions of 7.1 times in model parameters,32 times in feature dimension and 95.1％ in inferring complexity.The results demonstrate the validity and efficiency of the proposed method.关键词
深度学习/特征表示/知识蒸馏/模型压缩/人脸识别Key words
deep learning/feature representation/knowledge distillation/model compression/face recognition分类
信息技术与安全科学引用本文复制引用
葛仕明,赵胜伟,刘文瑜,李晨钰..基于深度特征蒸馏的人脸识别[J].北京交通大学学报,2017,41(6):27-33,41,8.基金项目
国家重点研发计划(2016YFC0801005) （2016YFC0801005）
国家自然科学基金(61772513 ,61402463) Foundation items:National Key Research and Development Plan (2016YFC0801005 ) （61772513 ,61402463）
National Natural Science Foundation of China (61772513 ,61402463) （61772513 ,61402463）
