Skip to main content

Novel Image Representations and Learning Tasks

Abstract Computer Vision as a eld has gone through signicant changes in the last decade.

The eld has seen tremendous success in designing learning systems with hand-crafted

features and in using representation learning to extract better features. In this dissertation

some novel approaches to representation learning and task learning are studied.

Multiple-instance learning which is generalization of supervised learning, is one

example of task learning that is discussed. In particular, a novel non-parametric k-

NN-based multiple-instance learning is proposed, which is shown to outperform other

existing approaches. This solution is applied to a diabetic retinopathy pathology

detection problem eectively.

In cases of representation learning, gen... (more)
Created Date 2017
Contributor Venkatesan, Ragav (Author) / Li, Baoxin (Advisor) / Turaga, Pavan (Committee member) / Yang, Yezhou (Committee member) / Davulcu, Hasan (Committee member) / Arizona State University (Publisher)
Subject Computer science / Dataset Generality / Deep Learning / Image Representations / Mentee Networks / Multiple Instance Learning
Type Doctoral Dissertation
Extent 138 pages
Language English
Reuse Permissions All Rights Reserved
Note Doctoral Dissertation Computer Science 2017
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Full Text
27.5 MB application/pdf
Download Count: 110

Description Dissertation/Thesis