首页 > 论文 > 激光与光电子学进展 > 56卷 > 23期(pp:231502--1)

一种多任务的卷积神经网络目标分类算法

Object Classification Based on Multitask Convolutional Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出一种基于细粒度图像和多属性融合的多任务卷积神经网络(MTCNN)。该网络主要包含几个关键环节,首先在网络中增加标签输入层,复制并分离输入的多个标签,通过全连接层与多个任务相匹配,增加与标签数量相应的Softmax损失函数,来对多个任务进行反向传播;然后,使用显著性检测与角点检测相结合的方法,提取出原始图像中的细粒度图像用于MTCNN的数据输入,使神经网络提取到的目标特征具有独特性和区分性;最后,使用非线性激活函数PReLu,进一步提高网络的分类精度。通过在Car Dataset中进行多任务并行训练,测试精度较传统单个任务的分类精度提升10%,实验结果表明,MTCNN有较高的泛化能力,对于图像分类的精度有明显的提升。

Abstract

This paper proposes a multitask convolutional neural network (MTCNN) based on fine-grained images and multi-attribute fusion. The network mainly includes the following key links. First, the label input layer is added to the network; the input multiple labels are copied and separated, and then matched to multiple tasks with a fully connected layer. The Softmax loss function corresponding to the number of labels is added to backpropagate multiple tasks. Then, a fine-grained image in the original image is extracted by the combination of saliency detection and corner detection, and used as the input of MTCNN. The target features extracted by the neural network are more unique and distinguishable. Finally, the MTCNN uses the nonlinear activation function PReLu to further improve the classification accuracy of the network. This paper uses the MTCNN to perform multi-task parallel training in the Car Dataset and achieves a 10% improvement in the classification accuracy over the traditional single task. The results show that the MTCNN has high generalization performance and the accuracy of image classification is obviously improved.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.231502

所属栏目:机器视觉

基金项目:国家自然科学基金、中国博士后面上基金、河南省青年骨干教师资助课题、河南省博士后基金、河南省教育厅科学技术研究重点项目;

收稿日期:2019-04-12

修改稿日期:2019-05-27

网络出版日期:2019-12-01

作者单位    点击查看

张苗辉:河南大学大数据分析与处理河南省重点实验室, 河南 开封 475004河南大学数据与知识工程研究所, 河南 开封 475004
张博:河南大学大数据分析与处理河南省重点实验室, 河南 开封 475004
高诚诚:河南大学大数据分析与处理河南省重点实验室, 河南 开封 475004

联系人作者:张博(zhangbo208@163.com)

备注:国家自然科学基金、中国博士后面上基金、河南省青年骨干教师资助课题、河南省博士后基金、河南省教育厅科学技术研究重点项目;

【1】Al-Saffar A A M, Tao H, Talab M A. Review of deep convolution neural network in image classification . [C]∥2017 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications (ICRAMET), October 23-24, 2017, Jakarta, Indonesia. New York: IEEE. 2017, 26-31.

【2】He Z C, Zhao L Z, Chen C. Convolution neural network with multi-resolution feature fusion for facial expression recognition [J]. Laser & Optoelectronics Progress. 2018, 55(7): 071503.
何志超, 赵龙章, 陈闯. 用于人脸表情识别的多分辨率特征融合卷积神经网络 [J]. 激光与光电子学进展. 2018, 55(7): 071503.

【3】Li J N, Zhang B H. Face recognition by feature matching fusion combined with improved convolutional neural network [J]. Laser & Optoelectronics Progress. 2018, 55(10): 101504.
李佳妮, 张宝华. 特征匹配融合结合改进卷积神经网络的人脸识别 [J]. 激光与光电子学进展. 2018, 55(10): 101504.

【4】Hasan M S. An application of pre-trained CNN for image classification . [C]∥2017 20th International Conference of Computer and Information Technology (ICCIT), December 22-24, 2017, Dhaka, Bangladesh. New York: IEEE. 2017, 17575567.

【5】Yang P, Zhao P L, Gao X. Robust online multi-task learning with correlative and personalized structures [J]. IEEE Transactions on Knowledge and Data Engineering. 2017, 29(11): 2510-2521.

【6】Sun Y, Chen Y H, Wang X G, et al. Deep learning face representation by joint identification-verification . [C]∥Proceedings of the 27th International Conference on Neural Information Processing Systems, December 8-13, 2014, Montreal, Canada. Canada: NIPS. 2014, 1988-1996.

【7】Zhang Z P, Luo P, Loy C C, et al. Facial landmark detection by deep multi-task learning [M]. ∥Fleet D, Pajdla T, Schiele B, et al. Computer vision-ECCV 2014. Lecture notes in computer science. Cham: Springer. 2014, 8694: 94-108.

【8】Trottier L, Giguère P. -05-15)[2019-04-11] . https:∥arxiv. 2018, org/abs/1711: 00111.

【9】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017, 39(6): 1137-1149.

【10】Zhang N, Donahue J, Girshick R, et al. Part-based R-CNNs for fine-grained category detection [M]. ∥Fleet D, Pajdla T, Schiele B, et al. Computer vision-ECCV 2014. Lecture notes in computer science. Cham: Springer. 2014, 8689: 834-849.

【11】Peng Y X, He X T, Zhao J J. Object-part attention model for fine-grained image classification [J]. IEEE Transactions on Image Processing. 2018, 27(3): 1487-1500.

【12】He K, Gkioxari G, Dollár P, et al. Mask R-CNN . [C]∥The IEEE International Conference on Computer Vision (ICCV), October 22-29, 2017, Venice, Italy. New York: IEEE. 2017, 2961-2969.

【13】Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks . [C]∥Proceedings of the 25th International Conference on Neural Information Processing Systems, December 3-6, 2012, Lake Tahoe, Nevada Canada: NIPS. 2012, 1097-1105.

【14】Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions . [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 2015, 15523970.

【15】Simonyan K. -04-10)[2019-04-11] . https:∥arxiv. 2015, org/abs/1409: 1556.

【16】Zhang C, Bengio S, Hardt M, et al. -02-26)[2019-04-11] . https:∥arxiv. 2017, org/abs/1611: 03530.

【17】Zhang J, Zhao H D, Li Y H, et al. Classifier for recognition of fine-grained vehicle models under complex background [J]. Laser & Optoelectronics Progress. 2019, 56(4): 041501.
张洁, 赵红东, 李宇海, 等. 复杂背景下车型识别分类器 [J]. 激光与光电子学进展. 2019, 56(4): 041501.

【18】Zhang S L, Xie L B. Salient detection based on all convolutional feature combination [J]. Laser & Optoelectronics Progress. 2018, 55(10): 101502.
张松龙, 谢林柏. 基于全部卷积特征融合的显著性检测 [J]. 激光与光电子学进展. 2018, 55(10): 101502.

【19】He K M, Zhang X Y, Ren S Q, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification . [C]∥2015 IEEE International Conference on Computer Vision (ICCV), December 7-13, 2015, Santiago, Chile. New York: IEEE. 2015, 1026-1034.

引用该论文

Zhang Miaohui,Zhang Bo,Gao Chengcheng. Object Classification Based on Multitask Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231502

张苗辉,张博,高诚诚. 一种多任务的卷积神经网络目标分类算法[J]. 激光与光电子学进展, 2019, 56(23): 231502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF