计算机工程与应用2018，Vol.54Issue(8)：21-27,7.DOI:10.3778/j.issn.1002-8331.1801-0170
基于多任务卷积神经网络的车辆多属性识别
Vehicle multi-attribute recognition based on multi-task convolutional neural network
摘要
Abstract
Fine-grained vehicle identification is challenging,especially when the two vehicles differ in appearance and subtleness.However,the general neural network model ignores the connection between the additional attributes.This paper proposes a convolution neural network based on improved triplet loss training for vehicle multi-attribute learning, which is used to implement fine-grained vehicle identification. Specifically, by changing the structure of the traditional neural network,the vehicle identification problem is transformed into a multi-attribute learning problem.In this paper,the triplet loss function is improved to train the network to achieve fine-grained vehicle identification.At the same time,it cre-ates a multi-attribute vehicle data set and completes the training work.The results show the potential of the method.关键词
细粒度车辆识别/车辆多属性/多任务学习/卷积神经网络/度量学习/车辆多属性数据集Key words
fine-grained vehicle recognition/vehicle multi-attribute/multi-task learning/convolution neural network/metric learning/vehicle multi-attribute data分类
信息技术与安全科学引用本文复制引用
王耀玮,唐伦,刘云龙,陈前斌..基于多任务卷积神经网络的车辆多属性识别[J].计算机工程与应用,2018,54(8):21-27,7.基金项目
国家自然科学基金(No.61571073). （No.61571073）
