Login | Register

Learning Through Text-Image Pairs and Image Sequences


Learning Through Text-Image Pairs and Image Sequences

Lao, Qicheng (2019) Learning Through Text-Image Pairs and Image Sequences. PhD thesis, Concordia University.

[thumbnail of Lao_PhD_S2020.pdf]
Text (application/pdf)
Lao_PhD_S2020.pdf - Accepted Version


Many machine learning systems for artificial intelligence are biologically inspired, for example, the artificial neural networks (ANNs) have similar architecture as human brains, and convolutional neural networks (CNNs) are inspired by the observations from early study on animal's visual cortex system. The above two examples (ANNs and CNNs) are inspirations at the level of creating fundamental tools (e.g., neural networks) for a machine learning system. Another level of inspirations can come from the way human learn or respond that builds on top of the existing powerful learning tools, i.e., brains. In this thesis, we will focus on another type of inspiration that also belongs to the second level. It is based on the common practice that for an efficient learning or an optimal decision, human integrate all sources of available information in multiple views and leverage the reasoning of the underlying connections among them, i.e., multi-view learning. We address several problems in both medical and non-medical domains, including text-to-image synthesis, cell phenotype classification, histopathological malignancy diagnosis and disease progression learning, from the perspective of multi-view learning with an emphasis on learning the underlying connections among the multiple distinct feature sets representing the given multi-view data (i.e., image sequences in a unimodal setting and text-image pairs in a multi-modal setting).

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (PhD)
Authors:Lao, Qicheng
Institution:Concordia University
Degree Name:Ph. D.
Program:Computer Science
Date:October 2019
Thesis Supervisor(s):Fevens, Thomas
ID Code:986692
Deposited By: QICHENG LAO
Deposited On:25 Jun 2020 18:19
Last Modified:25 Jun 2020 18:19
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top