淡江大學機構典藏:Item 987654321/116995
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62797/95867 (66%)
Visitors : 3732793      Online Users : 384
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/116995


    Title: A study on the convolutional neural algorithm of image style transfer
    Authors: Yang, Fu Wen;Lin, Hwei Jen;Yen, Shwu-Huey;Wang, Chun-Hui
    Keywords: Max-pooling;back-propagation;style transfer;overfitting;deep convolutional neural networks;fully convolutional networks;receptive field;kernel;merge kernel
    Date: 2018-11-05
    Issue Date: 2019-09-17 12:10:53 (UTC+8)
    Abstract: Recently, deep convolutional neural networks have resulted in noticeable improvements in image classification and have been used to transfer artistic style of images. L. A. Gatys et al. proposed the use of a learned CNN (Convolutional Neural Network) architecture VGG to transfer image style, but problems occur during the back propagation process because there is a heavy computational load. This paper solves these problems, including the simplification of the computation of chains of derivatives, accelerating the computation of adjustments, and efficiently choosing weights for different energy functions. The experimental results show that the proposed solutions improve the computational efficiency and render the adjustment of weights for energy functions easier.
    Relation: International Journal of Pattern Recognition and Artificial Intelligence 33(5), P.1954020
    DOI: 10.1142/S021800141954020X
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML108View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback