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 2023-06-21 14:10
[Poster Presentation] Verification of the effectiveness of multitask learning for demosaicking and white-balancing
Yuki Nakagomi, Ryoya Takeuchi, Taishi Iriyama, Takashi Komuro (Saitama Univ)
Abstract (in Japanese) (See Japanese page) 
(in English) In this study, we conducted an investigation on the learning effectiveness of jointly training demosaicking and white balance in a multi-task learning. We used datasets that were designed for jointly training of demosaicking and white balance, as well as datasets for sepalately training each task. We employed ResNet and U-Net models for the experiments and performed tests using models trained jointly and models trained separately for each task. The test results were compared to evaluate the performance. The experimental results showed that the models trained jointly achieved improved subjective performance for demosaicking and white balance.
Keyword (in Japanese) (See Japanese page) 
(in English) White-Balance / Demosaicking / multitask learning / Convolutional neural network / / / /  
Reference Info. ITE Tech. Rep., vol. 47, no. 19, IST2023-25, pp. 19-22, June 2023.
Paper # IST2023-25 
Date of Issue 2023-06-14 (IST) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee IST  
Conference Date 2023-06-21 - 2023-06-21 
Place (in Japanese) (See Japanese page) 
Place (in English) Tokyo University of Science Morito Memorial Hall 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To IST 
Conference Code 2023-06-IST 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Verification of the effectiveness of multitask learning for demosaicking and white-balancing 
Sub Title (in English)  
Keyword(1) White-Balance  
Keyword(2) Demosaicking  
Keyword(3) multitask learning  
Keyword(4) Convolutional neural network  
1st Author's Name Yuki Nakagomi  
1st Author's Affiliation Saitama University (Saitama Univ)
2nd Author's Name Ryoya Takeuchi  
2nd Author's Affiliation Saitama University (Saitama Univ)
3rd Author's Name Taishi Iriyama  
3rd Author's Affiliation Saitama University (Saitama Univ)
4th Author's Name Takashi Komuro  
4th Author's Affiliation Saitama University (Saitama Univ)
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 ()
Speaker Author-1 
Date Time 2023-06-21 14:10:00 
Presentation Time 60 minutes 
Registration for IST 
Paper # IST2023-25 
Volume (vol) vol.47 
Number (no) no.19 
Page pp.19-22 
Date of Issue 2023-06-14 (IST) 

[Return to Top Page]

[Return to ITE Web Page]

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