Staff View
Unsupervised visual domain adaptation: a probabilistic approach

Descriptive

TitleInfo
Title
Unsupervised visual domain adaptation: a probabilistic approach
Name (type = personal)
NamePart (type = family)
Babagholami Mohamadabadi
NamePart (type = given)
Behnam
DisplayForm
Behnam Babagholami Mohamadabadi
Role
RoleTerm (authority = RULIB)
author
Name (type = personal)
NamePart (type = family)
Pavlovic
NamePart (type = given)
Vladimir
DisplayForm
Vladimir Pavlovic
Affiliation
Advisory Committee
Role
RoleTerm (authority = RULIB)
chair
Name (type = corporate)
NamePart
Rutgers University
Role
RoleTerm (authority = RULIB)
degree grantor
Name (type = corporate)
NamePart
School of Graduate Studies
Role
RoleTerm (authority = RULIB)
school
TypeOfResource
Text
Genre (authority = marcgt)
theses
OriginInfo
DateCreated (encoding = w3cdtf); (keyDate = yes); (qualifier = exact)
2020
DateOther (encoding = w3cdtf); (qualifier = exact); (type = degree)
2020-01
Language
LanguageTerm (authority = ISO 639-3:2007); (type = text)
English
Abstract (type = abstract)
Artificial intelligent and machine learning technologies have already achieved significant success in various applications (computer vision, natural language processing, speech recognition, etc.). Such methods work well only under a common assumption that training and test data are drawn from the same distribution. However, the curse of domain mismatch arises when the test data and the training data come from different distributions. In such distribution changes, most statistical models need to be rebuilt, using newly collected training data. In many real world applications, it is expensive or even impossible to collect the required training data and rebuild the models. One of the ultimate goals of the open ended learning systems is to take advantage of previous experience/ knowledge in dealing with similar future problems. Two levels of learning can be identified in such scenarios. One draws on the data by capturing the pattern and regularities which enables reliable predictions on new samples. The other starts from an acquired source of knowledge and focuses on how to generalise it to a new target concept; this is also known as transfer learning which is going to be the main focus of this thesis.

This thesis will focus on a family of transfer learning methods applied to the task of visual object recognition, specifically image classification. The visual recognition problem is central to computer vision research: many desired applications, from robotics to information retrieval, demand the ability to correctly identify categories, places, and objects. Transfer learning is a general term, and specific settings have been given specific names: when the learner has access to only unlabeled data from the target domain (where the model should perform) and labeled data from a different domain (the source), the problem is called unsupervised domain adaptation (DA).

The thesis focuses on four methods for this setting. The first one proposes a probabilistic latent variable model by learning projections from each domain to a latent (shared) space jointly with the classifier in the latent space, which simultaneously minimizes the domain disparity while maximizing the classifier’s discriminative power. Furthermore, the non-parametric nature of our adaptation model makes it possible to infer the latent space dimension automatically from data.

The second method is based on the Gaussian Process (GP): The GP allows us to induce a hypothesis space of classifiers from the posterior distribution of the latent random functions, turning the learning into a large-margin posterior separation problem.

The Third method is based on GANs: We introduce an adversarial discriminative discrepancy measure which takes advantage of auxiliary information available in the source and the target domains to better align the source and target distributions. Specifically, we leverage the cohesive clustering structure within individual data manifolds, associated with different tasks, to improve the alignment.

The last one addresses domain adaptation for multiple target domains. We propose an information theoretic approach for domain adaptation in the novel context of multiple target domains with unlabeled instances and one source domain with labeled instances. Our model aims to find a shared latent space common to all domains, while simultaneously accounting for the remaining private, domain-specific factors. Disentanglement of shared and private information is accomplished using a unified information-theoretic approach, which also serves to establish a stronger link between the latent representations and the observed data.

We conduct experiments on a wide range of image classification tasks. We test our proposed methods and show that, in all cases, leveraging knowledge from a related domain can improve performance when there are no labels available for direct training on the new target data.
Subject (authority = RUETD)
Topic
Computer Science
Subject (authority = local)
Topic
Domain adaptation
Subject (authority = LCSH)
Topic
Artificial intelligence
RelatedItem (type = host)
TitleInfo
Title
Rutgers University Electronic Theses and Dissertations
Identifier (type = RULIB)
ETD
Identifier
ETD_10498
PhysicalDescription
Form (authority = gmd)
InternetMediaType
application/pdf
InternetMediaType
text/xml
Extent
1 online resource (xvii, 109 pages) : illustrations
Note (type = degree)
Ph.D.
Note (type = bibliography)
Includes bibliographical references
RelatedItem (type = host)
TitleInfo
Title
School of Graduate Studies Electronic Theses and Dissertations
Identifier (type = local)
rucore10001600001
Location
PhysicalLocation (authority = marcorg); (displayLabel = Rutgers, The State University of New Jersey)
NjNbRU
Identifier (type = doi)
doi:10.7282/t3-6w3n-b863
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
Babagholami Mohamadabadi
GivenName
Behnam
Role
Copyright Holder
RightsEvent
Type
Permission or license
DateTime (encoding = w3cdtf); (qualifier = exact); (point = start)
2020-01-03 16:35:33
AssociatedEntity
Name
Behnam Babagholami Mohamadabadi
Role
Copyright holder
Affiliation
Rutgers University. School of Graduate Studies
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.
RightsEvent
Type
Embargo
DateTime (encoding = w3cdtf); (qualifier = exact); (point = start)
2020-01-31
DateTime (encoding = w3cdtf); (qualifier = exact); (point = end)
2022-01-30
Detail
Access to this PDF has been restricted at the author's request. It will be publicly available after January 30th, 2022.
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
DateCreated (point = end); (encoding = w3cdtf); (qualifier = exact)
2020-01-07T04:30:15
DateCreated (point = end); (encoding = w3cdtf); (qualifier = exact)
2020-01-07T04:30:15
ApplicationName
pdfTeX-1.40.18
Back to the top
Version 8.5.5
Rutgers University Libraries - Copyright ©2024