Files in this item

FilesDescriptionFormat

application/pdf

application/pdfSHIH-DISSERTATION-2017.pdf (36MB)
(no description provided)PDF

Description

Title:Learning visual tasks with selective attention
Author(s):Shih, Kevin Jonathan
Director of Research:Hoiem, Derek
Doctoral Committee Chair(s):Hoiem, Derek
Doctoral Committee Member(s):Lazebnik, Svetlana; Forsyth, David; Parikh, Devi
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:Ph.D.
Genre:Dissertation
Subject(s):Computer vision
visual attention
vqa
visual question answering
keypoint localization
part localization
image recognition
fine-grained image recognition
deep learning
multi-task learning
machine learning
Abstract:Knowing where to look in an image can significantly improve performance in computer vision tasks by eliminating irrelevant information from the rest of the input image, and by breaking down complex scenes into simpler and more familiar sub-components. We show that a framework for identifying multiple task-relevant regions can be learned in current state-of-the-art deep network architectures, resulting in significant gains in several visual prediction tasks. We will demonstrate both directly and indirectly supervised models for selecting image regions and show how they can improve performance over baselines by means of focusing on the right areas.
Issue Date:2017-07-11
Type:Thesis
URI:http://hdl.handle.net/2142/98359
Rights Information:Copyright 2017 Kevin Jonathan Shih
Date Available in IDEALS:2017-09-29
Date Deposited:2017-08


This item appears in the following Collection(s)

Item Statistics