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

Discriminative Optimization: Theory ...

Vongkulbhisal, Jayakorn.

Linked to FindBook

Google Book

Amazon

博客來

Discriminative Optimization: Theory and Applications to Computer Vision.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Discriminative Optimization: Theory and Applications to Computer Vision./
Author:	Vongkulbhisal, Jayakorn.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
Description:	138 p.
Notes:	Source: Dissertations Abstracts International, Volume: 79-10, Section: B.
Contained By:	Dissertations Abstracts International79-10B.
Subject:	Computer Engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10746763
ISBN:	9780355684384

Discriminative Optimization: Theory and Applications to Computer Vision.
Vongkulbhisal, Jayakorn.

Discriminative Optimization: Theory and Applications to Computer Vision. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 138 p.

Source: Dissertations Abstracts International, Volume: 79-10, Section: B.

Thesis (Ph.D.)--Carnegie Mellon University, 2018.

This item is not available from ProQuest Dissertations & Theses.

Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (i) designing a cost function with a local optimum at an acceptable solution, and (ii) developing an efficient numerical method to search for one (or multiple) of these local optima. While designing such functions is feasible in the noiseless case, the stability and location of local optima are mostly unknown under noise, occlusion, or missing data. In practice, this can result in undesirable local optima or not having a local optimum in the expected solution. On the other hand, numerical optimization algorithms in high-dimensional spaces are typically local and often rely on expensive first or second order information to guide the search. To overcome these limitations, we propose Discriminative Optimization (DO), a method that learns search directions from data without the need of a cost function. Specifically, DO learns a sequence of updates in the search space that leads to stationary points corresponding to the desired solutions. Using training data, DO can find solutions that are more robust to perturbation of real data, unlike conventional optimization which may fail if there is a mismatch between the cost function and the noise distribution. We provide a formal analysis of DO, proving its convergence in the training phase. We also explore the relation between DO and generalized convexity and monotonicity, and show that the conditions for the convergence of DO are broader than those required by convexity. In terms of applications, we illustrate DO's potential in the problems of 3D point cloud registration, camera pose estimation, and image denoising. We show that DO can generally outperform state-of-the-art algorithms in terms of accuracy, robustness to perturbations, and computational efficiency.

ISBN: 9780355684384Subjects--Topical Terms:

1567821
Computer Engineering.

Discriminative Optimization: Theory and Applications to Computer Vision.
LDR:03109nmm a2200349 4500 001 2208068
005 20190929184210.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9780355684384
035 $a (MiAaPQ)AAI10746763
035 $a (MiAaPQ)cmu:10203
035 $a AAI10746763
040 $a MiAaPQ $c MiAaPQ
100 1 $a Vongkulbhisal, Jayakorn. $3 3435080
245 1 0 $a Discriminative Optimization: Theory and Applications to Computer Vision.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 138 p.
500 $a Source: Dissertations Abstracts International, Volume: 79-10, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Torre, Fernando De la;Costeira, Joao P.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2018.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be added to any third party search indexes.
506 $a This item must not be sold to any third party vendors.
520 $a Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: (i) designing a cost function with a local optimum at an acceptable solution, and (ii) developing an efficient numerical method to search for one (or multiple) of these local optima. While designing such functions is feasible in the noiseless case, the stability and location of local optima are mostly unknown under noise, occlusion, or missing data. In practice, this can result in undesirable local optima or not having a local optimum in the expected solution. On the other hand, numerical optimization algorithms in high-dimensional spaces are typically local and often rely on expensive first or second order information to guide the search. To overcome these limitations, we propose Discriminative Optimization (DO), a method that learns search directions from data without the need of a cost function. Specifically, DO learns a sequence of updates in the search space that leads to stationary points corresponding to the desired solutions. Using training data, DO can find solutions that are more robust to perturbation of real data, unlike conventional optimization which may fail if there is a mismatch between the cost function and the noise distribution. We provide a formal analysis of DO, proving its convergence in the training phase. We also explore the relation between DO and generalized convexity and monotonicity, and show that the conditions for the convergence of DO are broader than those required by convexity. In terms of applications, we illustrate DO's potential in the problems of 3D point cloud registration, camera pose estimation, and image denoising. We show that DO can generally outperform state-of-the-art algorithms in terms of accuracy, robustness to perturbations, and computational efficiency.
590 $a School code: 0041.
650 4 $a Computer Engineering. $3 1567821
650 4 $a Computer science. $3 523869
690 $a 0464
690 $a 0984
710 2 $a Carnegie Mellon University. $b Electrical and Computer Engineering. $3 2094139
773 0 $t Dissertations Abstracts International $g 79-10B.
790 $a 0041
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10746763