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 2020-02-27 16:20
[Special Talk] Neighbor-Aware Approaches for Pixel Labeling
Ryosuke Furuta (TUS), Naoto Inoue, Toshihiko Yamasaki (UT)
Abstract (in Japanese) (See Japanese page) 
(in English) Pixel labeling is one of the most classical and important problems in the field of computer vision because it has a variety of applications. We tackle two major challenges of pixel labeling: (i) how to deal with the large solution space, and (ii) how to learn the relationships between neighbor labels effectively. For the first challenge, we present two neighbor-aware fast optimization methods. One is the fast optimization method for general pixel-labeling problems based on Markov random field (MRF) models where the smoothness between the neighbor labels is forced. The other is the fast optimization method for the special case of pixel-labeling problems where the neighbor labels are forced to be connected. For the second challenge, we present two novel neighbor-aware learning methods that boost the performance of pixel labeling. Based on the mathematical relationship between the fixed point iteration of dense conditional random field (CRF) and recurrent convolution, we present a new model based on dense CRF, which automatically learns the relationships between neighbor labels from training data and enables joint training with deep neural networks. In addition, we present a novel problem setting (pixelRL), and an effective neighbor-aware learning method for pixelRL named reward map convolution. PixelRL is a novel pixel-labeling problem combined with reinforcement learning, where the label is a sequence of actions at each pixel, and its objective is to maximize the accumulated total rewards at all pixels.
Keyword (in Japanese) (See Japanese page) 
(in English) Pixel labeling / Markov random field / conditional random field / reinforcement learning / / / /  
Reference Info. ITE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2020-02-27 - 2020-02-28 
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 IEICE-IE 
Conference Code 2020-02-HI-IE-ITS-MMS-ME-AIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Neighbor-Aware Approaches for Pixel Labeling 
Sub Title (in English)  
Keyword(1) Pixel labeling  
Keyword(2) Markov random field  
Keyword(3) conditional random field  
Keyword(4) reinforcement learning  
1st Author's Name Ryosuke Furuta  
1st Author's Affiliation Tokyo University of Science (TUS)
2nd Author's Name Naoto Inoue  
2nd Author's Affiliation The University of Tokyo (UT)
3rd Author's Name Toshihiko Yamasaki  
3rd Author's Affiliation The University of Tokyo (UT)
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 2020-02-27 16:20:00 
Presentation Time 60 
Registration for IEICE-IE 
Paper #  
Volume (vol) ITE-44 
Number (no)  
#Pages ITE- 
Date of Issue  

[Return to Top Page]

[Return to ITE Web Page]

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