ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2018-02-16 13:00
Study of Multi-Scale Residual Network for Image-to-Image Translation
Rei Endo, Yoshihiko Kawai, Takahiro Mochizuki (NHK)
Abstract (in Japanese) (See Japanese page) 
(in English) In recent years, deep neural networks have widely studied in various fields such as object recognition, scene classification, colorization of monochrome images, and region segmentation of images. Especially, image converting tasks, such as colorization and region segmentation, are studied actively in particular, and, various image-to-image translation neural network for the image converting tasks have been proposed. In this paper, we propose Multi-Scale Residual Network (MSRN) for image converting with parallel calculation paths of various spatial scale features of images. MSRN has a structure that holds features of multiple spatial scales in parallel and calculates residuals of the feature of each scale by using the features of all scales. As a result, it can be expected that a network can be obtained various local features on various spatial scales. MSRN is evaluated using MS-COCO Stuff for region segmentation, and the outline of the method and its result are shown.
Keyword (in Japanese) (See Japanese page) 
(in English) Deep neural network / Image-to-image translation / Residual unit / / / / /  
Reference Info. ITE Tech. Rep., vol. 42, no. 4, ME2018-35, pp. 319-322, Feb. 2018.
Paper # ME2018-35 
Date of Issue 2018-02-08 (MMS, HI, ME, AIT) 
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2018-02-15 - 2018-02-16 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2018-02-ITS-IE-MMS-HI-ME-AIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Study of Multi-Scale Residual Network for Image-to-Image Translation 
Sub Title (in English)  
Keyword(1) Deep neural network  
Keyword(2) Image-to-image translation  
Keyword(3) Residual unit  
1st Author's Name Rei Endo  
1st Author's Affiliation Japan Broadcasting Corporation (NHK)
2nd Author's Name Yoshihiko Kawai  
2nd Author's Affiliation Japan Broadcasting Corporation (NHK)
3rd Author's Name Takahiro Mochizuki  
3rd Author's Affiliation Japan Broadcasting Corporation (NHK)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Date Time 2018-02-16 13:00:00 
Presentation Time 15 
Registration for ME 
Paper # ITE-MMS2018-35,ITE-HI2018-35,ITE-ME2018-35,ITE-AIT2018-35 
Volume (vol) ITE-42 
Number (no) no.4 
Page pp.319-322 
#Pages ITE-4 
Date of Issue ITE-MMS-2018-02-08,ITE-HI-2018-02-08,ITE-ME-2018-02-08,ITE-AIT-2018-02-08 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan