首页 > 论文 > 激光与光电子学进展 > 57卷 > 6期(pp:61021--1)

一种面向移动端的图像风格迁移模型压缩算法

An Image Style Transformation Model Compression Algorithm for Mobile Terminal

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

摘要

基于Johoson等的图像风格转换网络模型,在保证网络性能的前提下,在原有的网络结构上,通过运用更高效的网络计算方法对原有残差网络进行优化。实验结果表明,改进后的方法在几乎不降低图像质量的前提下,一定程度上克服了图像风格迁移模型存储量大、计算代价高、计算资源消耗大、难以移植到移动端的问题。

Abstract

In this study, we propose an efficient network computing method based on Johoson’s image style transformation network model to optimize the original residual network for ensuring suitable network performance. The conducted experiments prove that the proposed method can solve the following problems: high storage and calculation cost associated with the image style transformation network model; massive consumption of the computing resources; and difficulty with respect to the transplantation to a mobile terminal without reducing the image quality.

中国激光微信矩阵
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.061021

所属栏目:图像处理

基金项目:国家自然科学基金、宁夏高等学校科学研究项目;

收稿日期:2019-09-11

修改稿日期:2019-11-19

网络出版日期:2020-03-01

作者单位    点击查看

裴斐:宁夏大学信息工程学院, 宁夏 银川 750021
刘进锋:宁夏大学信息工程学院, 宁夏 银川 750021
李崤河:宁夏大学信息工程学院, 宁夏 银川 750021

联系人作者:刘进锋(850683631@qq.com)

备注:国家自然科学基金、宁夏高等学校科学研究项目;

【1】Hertzmann A. Painterly rendering with curved brush strokes of multiple sizes . [C]∥Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, July 19-24, 1998, Orlando, Florida, USA. New York: ACM. 1998, 453-460.

【2】Hertzmann A, Jacobs C E, Oliver N, et al. Image analogies . [C]∥Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, August 12-17, 2001, Los Angeles, California, USA. New York: ACM. 2001, 327-340.

【3】Portilla J, Simoncelli E P. A parametric texture model based on joint statistics of complex wavelet coefficients [J]. International Journal of Computer Vision. 2000, 40(1): 49-70.

【4】Mao Y H, Gui X L, Li Q, et al. Study on application technology of deep learning [J]. Application Research of Computers. 2016, 33(11): 3201-3205.
毛勇华, 桂小林, 李前, 等. 深度学习应用技术研究 [J]. 计算机应用研究. 2016, 33(11): 3201-3205.

【5】Gatys L A, Ecker A S. -09-02)[2019-09-10] . https:∥arxiv.xilesou. 2015, top/abs/1508: 06576.

【6】Johnson J, Alahi A, Li F F. Perceptual losses for real-time style transfer and super-resolution [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Cham: Springer. 2016, 9906: 694-711.

【7】Ulyanov D, Vedaldi A. -11-06)[2019-09-10] . https:∥arxiv.xilesou. 2017, top/abs/1607: 08022.

【8】Zhang H. -11-16)[2019-09-10] . https:∥arxiv.xilesou. 2017, top/abs/1703: 06953.

【9】Du Z L, Shen H Y, Song G M, et al. Image style transfer based on improved CycleGAN [J]. Optics and Precision Engineering. 2019, 27(8): 1836-1844.
杜振龙, 沈海洋, 宋国美, 等. 基于改进CycleGAN的图像风格迁移 [J]. 光学精密工程. 2019, 27(8): 1836-1844.

【10】Yang F W, Lin H J, Yen S H, et al. A study on the convolutional neural algorithm of image style transfer [J]. International Journal of Pattern Recognition and Artificial Intelligence. 2019, 33(5): 1954020.

【11】Simonyan K. -04-10)[2019-09-10] . https:∥arxiv.xilesou. 2015, top/abs/1409: 1556.

【12】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition . [C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 26-July 1, 2016, Las Vegas, Nevada. New York: IEEE. 2016, 770-778.

【13】Ji R R, Lin S H, Chao F, et al. Deep neural network compression and acceleration: a review [J]. Journal of Computer Research and Development. 2018, 55(9): 1871-1888.
纪荣嵘, 林绍辉, 晁飞, 等. 深度神经网络压缩与加速综述 [J]. 计算机研究与发展. 2018, 55(9): 1871-1888.

【14】Talebi H, Milanfar P. NIMA: neural image assessment [J]. IEEE Transactions on Image Processing. 2018, 27(8): 3998-4011.

【15】Murray N, Marchesotti L, Perronnin F. AVA: a large-scale database for aesthetic visual analysis . [C]∥2012 IEEE Conference on Computer Vision and Pattern Recognition, June 16-21, 2012, Providence, RI, USA. New York: IEEE. 2012, 2408-2415.

引用该论文

Pei Fei,Liu Jinfeng,Li Xiaohe. An Image Style Transformation Model Compression Algorithm for Mobile Terminal[J]. Laser & Optoelectronics Progress, 2020, 57(6): 061021

裴斐,刘进锋,李崤河. 一种面向移动端的图像风格迁移模型压缩算法[J]. 激光与光电子学进展, 2020, 57(6): 061021

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