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 2020-05-29 14:30
A method for analyze causes of deterioration of predict quality when Deep Learning is applied to instance segmentation
Tomonori Kubota, Takanori Nakao, Masafumi Katoh, Eiji Yoshida, Hidenobu Miyoshi (Fujitsu Lab.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this paper, we propose a method to analyze the cause of deterioration of prediction accuracy in instance segmentation by deep learning. We have proposed a method to analyze the cause of deterioration of prediction accuracy in object recognition and object detection. This method is extended to instance segmentation (Mask Scoring R-CNN). This method extracts and visualizes the cause at the pixel grain size in the image (input image) in which the quality of the prediction result deteriorates. And, by applying the cause information of the pixel grain size extracted by this technique to the input image, it can be corrected to the image with improved prediction accuracy. That is, it can be shown that the cause information extracted by this method correctly represents the cause.
Keyword (in Japanese) (See Japanese page) 
(in English) deep learning / convolutional neural network / video analysis / segmentation / XAI / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee IEICE-MI IEICE-IE IEICE-SIP IEICE-BioX IST ME  
Conference Date 2020-05-28 - 2020-05-29 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image and signal processing/analysis/AI technology, and their application 
Paper Information
Registration To IEICE-IE 
Conference Code 2020-05-MI-IE-SIP-BioX-IST-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A method for analyze causes of deterioration of predict quality when Deep Learning is applied to instance segmentation 
Sub Title (in English)  
Keyword(1) deep learning  
Keyword(2) convolutional neural network  
Keyword(3) video analysis  
Keyword(4) segmentation  
Keyword(5) XAI  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Tomonori Kubota  
1st Author's Affiliation Fujitsu Laboratories LTD. (Fujitsu Lab.)
2nd Author's Name Takanori Nakao  
2nd Author's Affiliation Fujitsu Laboratories LTD. (Fujitsu Lab.)
3rd Author's Name Masafumi Katoh  
3rd Author's Affiliation Fujitsu Laboratories LTD. (Fujitsu Lab.)
4th Author's Name Eiji Yoshida  
4th Author's Affiliation Fujitsu Laboratories LTD. (Fujitsu Lab.)
5th Author's Name Hidenobu Miyoshi  
5th Author's Affiliation Fujitsu Laboratories LTD. (Fujitsu Lab.)
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
Date Time 2020-05-29 14:30:00 
Presentation Time 20 
Registration for IEICE-IE 
Paper #  
Volume (vol) ITE-44 
Number (no)  
Page  
#Pages ITE- 
Date of Issue  


[Return to Top Page]

[Return to ITE Web Page]


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