COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

New Views of Deep Metric Learning
by Xuan, Hong, D.Sc., The George Washington University, 2021, 112; 28319772
Abstract (Summary)

Measuring image similarity is at the core of many computer vision problems. It is the basis for many vision applications such as object recognition and classification, image search and retrieval, person re-identification, face recognition, and recommendation systems. Deep Metric Learning provides a solution to learning a non-linear mapping function with deep networks to map input data into a high-dimension embedding space where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. In this thesis, I systematically investigate multiple topics in training deep metric learning tasks, such as loss function design, sampling strategies, optimization, effective visualization, and ensemble methods, and provide new views on those topics. The views can be summarized into four works: DREML, Easy Positive mining, Selectively Contrastive Triplet loss, and Gradient Framework. Each of them addresses specific problems in training deep metric learning tasks and improves image retrieval result over many datasets.

Indexing (document details)
Advisor: Pless, Robert
Commitee: Youssef, Abdou, Caliskan, Aylin, Weinberger, Kilian
School: The George Washington University
Department: Computer Science
School Location: United States -- District of Columbia
Source: DAI-B 82/10(E), Dissertation Abstracts International
Subjects: Computer science, Artificial intelligence
Keywords: Deep Metric Learning, Image retrieval, Triplet loss, Object recognition
Publication Number: 28319772
ISBN: 9798597069883
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy