dc.contributor.advisor Guo, Yuhong dc.creator Ye, Meng dc.date.accessioned 2020-11-05T16:15:50Z dc.date.available 2020-11-05T16:15:50Z dc.date.issued 2019 dc.identifier.uri http://hdl.handle.net/20.500.12613/3885 dc.description.abstract Data is a critical component in a supervised machine learning system. Many successful applications of learning systems on various tasks are based on a large amount of labeled data. For example, deep convolutional neural networks have surpassed human performance on ImageNet classification, which consists of millions of labeled images. However, one challenge in conventional supervised learning systems is their generalization ability. Once a model is trained on a specific dataset, it can only perform the task on those \emph{seen} classes and cannot be used for novel \emph{unseen} classes. In order to make the model work on new classes, one has to collect and label new data and then re-train the model. However, collecting data and labeling them is labor-intensive and costly, in some cases, it is even impossible. Also, there is an enormous amount of different tasks in the real world. It is not applicable to create a dataset for each of them. These problems raise the need for Transfer Learning, which is aimed at using data from the \emph{source} domain to improve the performance of a model on the \emph{target} domain, and these two domains have different data or different tasks. One specific case of transfer learning is Zero-Shot Learning. It deals with the situation where \emph{source} domain and \emph{target} domain have the same data distribution but do not have the same set of classes. For example, a model is given animal images of cat' and dog' for training and will be tested on classifying 'tiger' and 'wolf' images, which it has never seen. Different from conventional supervised learning, Zero-Shot Learning does not require training data in the \emph{target} domain to perform classification. This property gives ZSL the potential to be broadly applied in various applications where a system is expected to tackle unexpected situations. In this dissertation, we develop algorithms that can help a model effectively transfer visual and semantic knowledge learned from \emph{source} task to \emph{target} task. More specifically, first we develop a model that learns a uniform visual representation of semantic attributes, which help alleviate the domain shift problem in Zero-Shot Learning. Second, we develop an ensemble network architecture with a progressive training scheme, which transfers \emph{source} domain knowledge to the \emph{target} domain in an end-to-end manner. Lastly, we move a step beyond ZSL and explore Label-less Classification, which transfers knowledge from pre-trained object detectors into scene classification tasks. Our label-less classification takes advantage of word embeddings trained from unorganized online text, thus eliminating the need for expert-defined semantic attributes for each class. Through comprehensive experiments, we show that the proposed methods can effectively transfer visual and semantic knowledge between tasks, and achieve state-of-the-art performances on standard datasets. dc.format.extent 96 pages dc.language.iso eng dc.publisher Temple University. Libraries dc.relation.ispartof Theses and Dissertations dc.rights IN COPYRIGHT- This Rights Statement can be used for an Item that is in copyright. Using this statement implies that the organization making this Item available has determined that the Item is in copyright and either is the rights-holder, has obtained permission from the rights-holder(s) to make their Work(s) available, or makes the Item available under an exception or limitation to copyright (including Fair Use) that entitles it to make the Item available. dc.rights.uri http://rightsstatements.org/vocab/InC/1.0/ dc.subject Computer Science dc.subject Artificial Intelligence dc.subject Classification dc.subject Image Recognition dc.subject Transfer Learning dc.subject Zero-shot Learning dc.title VISUAL AND SEMANTIC KNOWLEDGE TRANSFER FOR NOVEL TASKS dc.type Text dc.type.genre Thesis/Dissertation dc.contributor.committeemember Shi, Justin Y. dc.contributor.committeemember Vucetic, Slobodan dc.contributor.committeemember Dragut, Eduard Constantin dc.contributor.committeemember Du, Liang dc.description.department Computer and Information Science dc.relation.doi http://dx.doi.org/10.34944/dspace/3867 dc.ada.note For Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu dc.description.degree Ph.D. refterms.dateFOA 2020-11-05T16:15:50Z
﻿

### Files in this item

Name:
Ye_temple_0225E_13822.pdf
Size:
3.042Mb
Format:
PDF