Show simple item record

FieldValueLanguage
dc.contributor.authorZhang, Weichen
dc.date.accessioned2021-07-20T00:16:23Z
dc.date.available2021-07-20T00:16:23Z
dc.date.issued2021en_AU
dc.identifier.urihttps://hdl.handle.net/2123/25719
dc.description.abstractDeep neural networks, which usually require a large amount of labelled data during training process, have achieved significant progress in many practical applications in this information era. Besides, due to the different environments and the variation of sensors used for data collection, it often brings difficulties for general supervised deep learning methods to perform well in various scenarios. Therefore, deep transfer learning methods, especially the deep domain adaptation methods are developed to exploit the domain-invariant intrinsic features and improve the generalization capability of the deep neural networks. This thesis addresses several issues of domain adaptation for multiple practical applications. The main contributions of this thesis are listed below. First, a comprehensive literature review for deep learning, transfer learning, domain adaptation and multiple visual applications is presented to provide better understanding of the background of this thesis. Second, a general domain adaptation method called Collaborative and Adversarial Network (CAN) is introduced to jointly learn domain-specific and domain-invariant features through domain-collaborative and domain-adversarial training of deep neural networks. Third, a multi-modality domain adaptation framework called Progressive Modality Cooperation (PMC) is proposed for domain adaptation with multi-modality input, and is additionally extended to PMC using Privileged Information (PMC-PI) to deal with the domain adaptation problem when some modalities are missing in the target domain. Fourth, the Scale-aware and Range-aware Domain Adaptation Network (SRDAN) is designed to deal with the Cross-dataset 3D Object Detection task, where objects with similar geometric characteristics are guided to be aligned between two domains. Last, we give future research directions of domain adaptation.en_AU
dc.language.isoenen_AU
dc.subjectDomain Adaptationen_AU
dc.subjectTransfer Learningen_AU
dc.titleDeep Domain Adaptation for Visual Recognitionen_AU
dc.typeThesis
dc.type.thesisDoctor of Philosophyen_AU
dc.rights.otherThe author retains copyright of this thesis. It may only be used for the purposes of research and study. It must not be used for any other purposes and may not be transmitted or shared with others without prior permission.en_AU
usyd.facultySeS faculties schools::Faculty of Engineering::School of Electrical and Information Engineeringen_AU
usyd.degreeDoctor of Philosophy Ph.D.en_AU
usyd.awardinginstThe University of Sydneyen_AU
usyd.advisorXU, DONG
usyd.advisorOUYANG, WANLI


Show simple item record

Associated file/s

Associated collections

Show simple item record

There are no previous versions of the item available.