Staff View
A novel framework for understanding atypical images

Descriptive

TitleInfo
Title
A novel framework for understanding atypical images
Name (type = personal)
NamePart (type = family)
Saleh
NamePart (type = given)
Babak
NamePart (type = date)
1987-
DisplayForm
Babak Saleh
Role
RoleTerm (authority = RULIB)
author
Name (type = personal)
NamePart (type = family)
Elgammal
NamePart (type = given)
Ahmed
DisplayForm
Ahmed Elgammal
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
chair
Name (type = personal)
NamePart (type = family)
Feldman
NamePart (type = given)
Jacob
DisplayForm
Jacob Feldman
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
internal member
Name (type = personal)
NamePart (type = family)
Bekris
NamePart (type = given)
Kostas
DisplayForm
Kostas Bekris
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
internal member
Name (type = personal)
NamePart (type = family)
Parikh
NamePart (type = given)
Devi
DisplayForm
Devi Parikh
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
outside member
Name (type = corporate)
NamePart
Rutgers University
Role
RoleTerm (authority = RULIB)
degree grantor
Name (type = corporate)
NamePart
Graduate School - New Brunswick
Role
RoleTerm (authority = RULIB)
school
TypeOfResource
Text
Genre (authority = marcgt)
theses
OriginInfo
DateCreated (qualifier = exact)
2017
DateOther (qualifier = exact); (type = degree)
2017-01
CopyrightDate (encoding = w3cdtf); (qualifier = exact)
2017
Place
PlaceTerm (type = code)
xx
Language
LanguageTerm (authority = ISO639-2b); (type = code)
eng
Abstract (type = abstract)
In the past few years, there has been a tremendous amount of progress in the field of computer vision. As of now, we have reliable object detectors and classifiers that can recognize thousands of object categories. However, the ultimate goal of computer vision is to build systems that can understand and reason about images, far beyond scene categorization and object detection. In this thesis, algorithms have been proposed to empower computers with the human-level ability of detecting and reasoning about images that are understudied in the mainstream computer vision community. In chapter 1, we open the conversation about abnormality detection, by discussing how hu- mans form visual concepts (e.g. an object category) and perceive meaningful deviations from these learned concepts as signals for abnormality. However, there is not a comprehensive study about what factors lead humans in this decision-making process. In chapter 2 we collect the first dataset of abnormal images from the web. Conduct several human subject experiments, and perform a thorough set of analysis to discover hidden factors in human judgment about abnormality. These analyses lead us to propose a taxonomy of comprehensive reasons of ab- normality in images. Inspired by human reasoning, we address the problem of detecting abnormal objects and reasoning about their abnormality in terms of visual attributes, such as irregular shape, texture or color (chapter 3). Although our computational models are learned without seeing any ab- normal objects at training time, but still are capable of detecting and reasoning about abnormal images at the test time. In chapter 4 we develop probabilistic frameworks to model typical images and find atypical images as a meaningful deviation from this model. In chapter 5, we use the typicality scores of images and objects to improve the generalization capacity of the state- of-the-art Convolutional Neural Networks (CNN) for the task of object classification. We train these CNN models by minimizing a weighted loss function that incorporates in the typicality scores of samples. Our experiments show that this training strategy results in more generalized classifiers, which can be applied even to the extent of abnormal images. In chapter 6 of this thesis, we study two problems that extend our framework for abnormality detection to special cases. We develop algorithms for detecting and localizing attributes in images. In addition to the application of localized attributes for the problem of abnormality detection, we show that fine-grained object categorization benefit from such rich information as well. We also propose algorithms to learn visual classifiers directly from the textual description of an object category. This zero-shot learning strategy extends the abnormality detection framework to object categories that are not present at the time of training. We close this thesis by discussing the main contributions and some future work.
Subject (authority = RUETD)
Topic
Computer Science
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Identifier (type = RULIB)
ETD
Identifier
ETD_7795
PhysicalDescription
Form (authority = gmd)
electronic resource
InternetMediaType
application/pdf
InternetMediaType
text/xml
Extent
1 online resource (xvi, 181 p. : ill.)
Note (type = degree)
Ph.D.
Note (type = bibliography)
Includes bibliographical references
Subject (authority = ETD-LCSH)
Topic
Machine learning
Subject (authority = ETD-LCSH)
Topic
Computer vision
Subject (authority = ETD-LCSH)
Topic
Image processing
Note (type = statement of responsibility)
by Babak Saleh
RelatedItem (type = host)
TitleInfo
Title
Graduate School - New Brunswick Electronic Theses and Dissertations
Identifier (type = local)
rucore19991600001
Location
PhysicalLocation (authority = marcorg); (displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier (type = doi)
doi:10.7282/T36W9DH1
Genre (authority = ExL-Esploro)
ETD doctoral
Back to the top

Rights

RightsDeclaration (ID = rulibRdec0006)
The author owns the copyright to this work.
RightsHolder (type = personal)
Name
FamilyName
Saleh
GivenName
Babak
Role
Copyright Holder
RightsEvent
Type
Permission or license
DateTime (encoding = w3cdtf); (qualifier = exact); (point = start)
2016-12-22 09:57:19
AssociatedEntity
Name
Babak Saleh
Role
Copyright holder
Affiliation
Rutgers University. Graduate School - New Brunswick
AssociatedObject
Type
License
Name
Author Agreement License
Detail
I hereby grant to the Rutgers University Libraries and to my school the non-exclusive right to archive, reproduce and distribute my thesis or dissertation, in whole or in part, and/or my abstract, in whole or in part, in and from an electronic format, subject to the release date subsequently stipulated in this submittal form and approved by my school. I represent and stipulate that the thesis or dissertation and its abstract are my original work, that they do not infringe or violate any rights of others, and that I make these grants as the sole owner of the rights to my thesis or dissertation and its abstract. I represent that I have obtained written permissions, when necessary, from the owner(s) of each third party copyrighted matter to be included in my thesis or dissertation and will supply copies of such upon request by my school. I acknowledge that RU ETD and my school will not distribute my thesis or dissertation or its abstract if, in their reasonable judgment, they believe all such rights have not been secured. I acknowledge that I retain ownership rights to the copyright of my work. I also retain the right to use all or part of this thesis or dissertation in future works, such as articles or books.
Copyright
Status
Copyright protected
Availability
Status
Open
Reason
Permission or license
Back to the top

Technical

RULTechMD (ID = TECHNICAL1)
ContentModel
ETD
OperatingSystem (VERSION = 5.1)
windows xp
CreatingApplication
Version
1.5
ApplicationName
pdfTeX-1.40.16
DateCreated (point = end); (encoding = w3cdtf); (qualifier = exact)
2016-12-22T09:53:25
DateCreated (point = end); (encoding = w3cdtf); (qualifier = exact)
2016-12-22T09:53:25
Back to the top
Version 8.4.8
Rutgers University Libraries - Copyright ©2022