Home
Resource
Advanced zero-shot learning: object recognition with semantic descriptions
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(14.78 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Zhu, Yizhe. Advanced zero-shot learning: object recognition with semantic descriptions. Retrieved from https://doi.org/doi:10.7282/t3-1wct-bs46

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleAdvanced zero-shot learning: object recognition with semantic descriptions
NameZhu, Yizhe (author); Elgammal, Ahmed (chair); Elgammal, Ahmed (member); Zhang, Yongfeng (member); de Melo, Gerard (member); Ling, Haibin (member); Rutgers University; School of Graduate Studies
Date Created2021
Other Date2021-10 (degree)
SubjectComputer science, Language and vision, Object recognition, Semantic description, Zero-shot learning
Extent1 online resource (xiv, 85 pages) : illustrations
DescriptionHuman beings have the remarkable ability to recognize novel visual objects only based on the description with semantic concepts. Deep learning, however, often requires a large number of labeled training samples to achieve superior performance. It's laborious, expensive, and difficult to collect sufficient labeled data for each object because the distribution of data among categories in the real world is long-tailed. Therefore, it is in great demand to research how to recognize novel visual objects with no visual data being seen.  Zero-shot learning aims to expand the learned knowledge from seen objects, of which we have training samples, to unseen objects, of which we have no training data. To mimic the human ability to recognize novel objects, zero-shot learning leverages semantic descriptions of classes to bridge the gap between both seen and unseen classes. This thesis concerns zero-shot learning from three aspects: the semantic descriptions of classes, the discriminative visual representation of images, and the algorithm design. We first present a visual-semantic embedding-based method that embeds visual data and semantic data to a shared embedding space. Images are encoded by a part-based CNN that detects bird parts and learns part-specific representation. The sparsity regularizer forces the models to connect text terms to their relevant parts and suppress connections to non-visual text terms without any part-text annotations. Then we propose a novel algorithm to leverage generative models to synthesize the visual data of unseen categories based on semantic descriptions and convert zero-shot learning to a conventional object recognization problem. Finally, we shift our focus to learning better discriminative visual representation of images in part-level for zero-shot learning in a weekly-supervised manner. Experiment results showed that our models significantly improves the performance of zero-shot learning in different settings. 
NotePh.D.
NoteIncludes bibliographical references
Genretheses
Persistent URLhttps://doi.org/doi:10.7282/t3-1wct-bs46
LanguageEnglish
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024