Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Christopher_Menart_s_Master_s_Thesis.pdf (5.35 MB)
ETD Abstract Container
Abstract Header
Global-Context Refinement for Semantic Image Segmentation
Author Info
Menart, Christopher J, Menart
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=osu1523462175806808
Abstract Details
Year and Degree
2018, Master of Science, Ohio State University, Computer Science and Engineering.
Abstract
Convolutional neural nets have been applied to the task of semantic image segmentation and surpassed previous methods. But even state-of-the-art systems fail on many portions of modern segmentation datasets. We observe that these failures are not random, but in most cases systematic and partially predictable. In particular, the confusion of a segmentation model is mostly stable. We propose compact descriptors of classifier behavior and of visual scene type. These descriptors can be applied in a Bayesian framework to reason about the reliability of predictions returned by a semantic segmentation model, and to correct mistakes in those results contingent on the ability to characterize images at the scene level. We demonstrate, using a competitive semantic segmentation model and several challenging datasets, that the upper bound of this approach is a great improvement in accuracy. The future work we describe has the potential to yield flexible and broad-ranging improvements to deep scene understanding and similar classification problems.
Committee
Jim Davis, Ph.D. (Advisor)
Eric Fosler-Lussier, Ph.D. (Committee Member)
Pages
52 p.
Subject Headings
Artificial Intelligence
;
Computer Science
Keywords
computer vision
;
artificial intelligence
;
deep learning
;
convolutional neural nets
;
semantic segmentation
;
image context
;
probabilistic inference
;
bayesian
;
PASCAL Context
;
NYUDv2
;
ADE20K
;
RefineNet
;
deep scene understanding
;
confusion matrices
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Menart, Menart, C. J. (2018).
Global-Context Refinement for Semantic Image Segmentation
[Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1523462175806808
APA Style (7th edition)
Menart, Menart, Christopher.
Global-Context Refinement for Semantic Image Segmentation.
2018. Ohio State University, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=osu1523462175806808.
MLA Style (8th edition)
Menart, Menart, Christopher. "Global-Context Refinement for Semantic Image Segmentation." Master's thesis, Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1523462175806808
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
osu1523462175806808
Download Count:
509
Copyright Info
© 2018, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.