DocumentCode :
37554
Title :
A Deep-Structured Fully Connected Random Field Model for Structured Inference
Author :
Wong, Alexander ; Shafiee, Mohammad Javad ; Siva, Parthipan ; Xiao Yu Wang
Author_Institution :
Dept. of Syst. Design Eng., Univ. of Waterloo, Waterloo, ON, Canada
Volume :
3
fYear :
2015
fDate :
2015
Firstpage :
469
Lastpage :
477
Abstract :
There has been significant interest in the use of fully connected graphical models and deep-structured graphical models for the purpose of structured inference. However, fully connected and deep-structured graphical models have been largely explored independently, leaving the unification of these two concepts ripe for exploration. A fundamental challenge with unifying these two types of models is in dealing with computational complexity. In this paper, we investigate the feasibility of unifying fully connected and deep-structured models in a computationally tractable manner for the purpose of structured inference. To accomplish this, we introduce a deep-structured fully connected random field (DFRF) model that integrates a series of intermediate sparse autoencoding layers placed between state layers to significantly reduce the computational complexity. The problem of image segmentation was used to illustrate the feasibility of using the DFRF for structured inference in a computationally tractable manner. Results in this paper show that it is feasible to unify fully connected and deep-structured models in a computationally tractable manner for solving structured inference problems such as image segmentation.
Keywords :
image segmentation; learning (artificial intelligence); DFRF model; computational complexity; deep-structured fully connected random field model; deep-structured graphical models; image segmentation; intermediate sparse autoencoding layers; structured inference; Graph theory; Image segmentation; Inference algorithms; Random processes; Structured inference; Random fields; deep structured; fully connected; image; learning; random fields; segmentation; structured inference;
fLanguage :
English
Journal_Title :
Access, IEEE
Publisher :
ieee
ISSN :
2169-3536
Type :
jour
DOI :
10.1109/ACCESS.2015.2425304
Filename :
7091871
Link To Document :
بازگشت