東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Novel Image Representations and Lear...

Venkatesan, Ragav.

Linked to FindBook

Google Book

Amazon

博客來

Novel Image Representations and Learning Tasks.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Novel Image Representations and Learning Tasks./
Author:	Venkatesan, Ragav.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	138 p.
Notes:	Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
Contained By:	Dissertation Abstracts International79-03B(E).
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10642755
ISBN:	9780355505559

Novel Image Representations and Learning Tasks.
Venkatesan, Ragav.

Novel Image Representations and Learning Tasks. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 138 p.

Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.

Thesis (Ph.D.)--Arizona State University, 2017.

Computer Vision as a field has gone through significant changes in the last decade. The field 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 effectively.

ISBN: 9780355505559Subjects--Topical Terms:

523869
Computer science.

Novel Image Representations and Learning Tasks.
LDR:02121nmm a2200301 4500 001 2156488
005 20180517112612.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355505559
035 $a (MiAaPQ)AAI10642755
035 $a (MiAaPQ)asu:17450
035 $a AAI10642755
040 $a MiAaPQ $c MiAaPQ
100 1 $a Venkatesan, Ragav. $3 3344247
245 1 0 $a Novel Image Representations and Learning Tasks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 138 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-03(E), Section: B.
500 $a Adviser: Baoxin Li.
502 $a Thesis (Ph.D.)--Arizona State University, 2017.
520 $a Computer Vision as a field has gone through significant changes in the last decade. The field 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 effectively.
520 $a In cases of representation learning, generality of neural features are investigated first. This investigation leads to some critical understanding and results in feature generality among datasets. The possibility of learning from a mentor network instead of from labels is then investigated. Distillation of dark knowledge is used to efficiently mentor a small network from a pre-trained large mentor network. These studies help in understanding representation learning with smaller and compressed networks.
590 $a School code: 0010.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a Arizona State University. $b Computer Science. $3 1676136
773 0 $t Dissertation Abstracts International $g 79-03B(E).
790 $a 0010
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10642755