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 2022-05-19 09:40
Variational Autoencoders Conditioned by Contrastive Features as Style-Feature Extractors
Suguru Yasutomi, Toshihisa Tanaka (TUAT)
Abstract (in Japanese) (See Japanese page) 
(in English) Extracting style features is crucial for investigating the characteristics of data. This paper proposes a variational autoencoder that extracts style features by adding features of contrastive learning as a condition. We can regard the contrastive features as style-independent by assuming that the data augmentation is a perturbation of style. We add the style-independent contrastive features to the input of the decoder, aiming to make the encoder cover the style features for reconstruction. Experiments on MNIST show qualitatively that the proposed method can extract style features. Additional experiments on DAISO-100 evaluate the performance of extracting style quantitatively.
Keyword (in Japanese) (See Japanese page) 
(in English) contrastive learning / variational autoencoders / style extraction / / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN  
Download PDF

Conference Information
Committee IEICE-SIP IEICE-BioX IEICE-IE IEICE-MI IST ME  
Conference Date 2022-05-19 - 2022-05-20 
Place (in Japanese) (See Japanese page) 
Place (in English) Kumamoto University 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To IEICE-SIP 
Conference Code 2022-05-SIP-BioX-IE-MI-IST-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Variational Autoencoders Conditioned by Contrastive Features as Style-Feature Extractors 
Sub Title (in English)  
Keyword(1) contrastive learning  
Keyword(2) variational autoencoders  
Keyword(3) style extraction  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Suguru Yasutomi  
1st Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
2nd Author's Name Toshihisa Tanaka  
2nd Author's Affiliation Tokyo University of Agriculture and Technology (TUAT)
3rd Author's Name  
3rd Author's Affiliation ()
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 ()
Speaker Author-1 
Date Time 2022-05-19 09:40:00 
Presentation Time 20 minutes 
Registration for IEICE-SIP 
Paper #  
Volume (vol) vol.46 
Number (no)  
Page  
#Pages  
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]
The Institute of Image Information and Television Engineers (ITE), Japan