IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
... (for ESS/CS/ES/ISS)
Tech. Rep. Archives
... (for ES/CS)
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2018-10-25 11:10
Improvement of Classification Accuracy for Imbalanced Training Data by CasNet
Takuro Oki, Ryusuke Miyamoto (Meiji Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Imbalanced samples composed of limited number of positive samples corresponding to objects and huge number of negative samples extracted from background regions reduces the accuracy of visual object detection. To solve this problem, this paper proposes a novel convolutional neural network named "CasNet". CasNet introduces cascade structure that is used for rapid and accurate object detector in order to reduce the number of negative. The CasNet become a cascade stage when it is attached to a layer of existing convolutinoal neural networks to construct cascaded classifier. Each stage composed of a CasNet peforms two-class classification to reject easy negatives corresponding to background regions. By this early rejection of easy negatives, a main network can be trained to classify more complex samples. Experimental results using a dataset created from the PASCAL VOC2012 dataset showed that higher accuracy was obtained at less training iterations if CasNets were attached to VGG16 appropriately.
Keyword (in Japanese) (See Japanese page) 
(in English) Visual object detection / Convolutional neural network / Data imbalance problem / / / / /  
Reference Info. IEICE Tech. Rep., vol. 118, no. 264, SIS2018-13, pp. 19-24, Oct. 2018.
Paper # SIS2018-13 
Date of Issue 2018-10-18 (SIS) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380

Conference Information
Committee SIS ITE-BCT  
Conference Date 2018-10-25 - 2018-10-26 
Place (in Japanese) (See Japanese page) 
Place (in English) Kyoto University Clock Tower Centennial Hall 
Topics (in Japanese) (See Japanese page) 
Topics (in English) System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. 
Paper Information
Registration To SIS 
Conference Code 2018-10-SIS-BCT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Improvement of Classification Accuracy for Imbalanced Training Data by CasNet 
Sub Title (in English)  
Keyword(1) Visual object detection  
Keyword(2) Convolutional neural network  
Keyword(3) Data imbalance problem  
1st Author's Name Takuro Oki  
1st Author's Affiliation Meiji University (Meiji Univ.)
2nd Author's Name Ryusuke Miyamoto  
2nd Author's Affiliation Meiji University (Meiji Univ.)
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 ()
Date Time 2018-10-25 11:10:00 
Presentation Time 20 
Registration for SIS 
Paper # IEICE-SIS2018-13 
Volume (vol) IEICE-118 
Number (no) no.264 
Page pp.19-24 
#Pages IEICE-6 
Date of Issue IEICE-SIS-2018-10-18 

[Return to Top Page]

[Return to IEICE Web Page]

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan