國立虎尾科技大學 |

Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Exploring the Frontier of Graph-based Approaches for Image and Document Analysis./
Author:	Chen, Bohan.
Description:	1 online resource (225 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Applied mathematics. -
Online resource:	click for full text (PQDT)
ISBN:	9798382785912

Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.
Chen, Bohan.

Exploring the Frontier of Graph-based Approaches for Image and Document Analysis. - 1 online resource (225 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2024.

Includes bibliographical references

Graph-based machine learning is a powerful framework for analyzing and understanding complex data structures in various domains. This thesis introduces novel graph-based methods in multiple image analysis tasks, including classification, segmentation, and unmixing, as well as their application in enhancing large language models. The key contributions include: (1) the development of new core-set selection and batch active learning methods that significantly improve the efficiency of graph-based active learning while maintaining its effectiveness; (2) the integration of graph learning, active learning, and advanced feature embedding methods to construct pipelines for SAR image classification and multi- or hyperspectral image segmentation, outperforming neural network-based classifiers or segmenters in semi-supervised learning tasks with limited training data; (3) the incorporation of graph-based regularization into the optimization problem of hyperspectral unmixing, enabling the utilization of a small amount of labeled pixels to greatly improve the performance compared to blind unmixing; and (4) the extension of graph Laplacian-based methods to automatically construct knowledge graphs in combination with large language models, enhancing their information retrieval and response generation capabilities.The proposed methods showcase the effectiveness and versatility of graph-based approaches in addressing challenges such as limited labeled data, computational efficiency, and knowledge representation. The thesis demonstrates the potential of graph-based methods in pushing the boundaries of image and document analysis and their applicability in a wide range of machine learning problems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382785912Subjects--Topical Terms:

1069907
Applied mathematics.
Subjects--Index Terms:

Active learningIndex Terms--Genre/Form:

554714
Electronic books.

Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.
LDR:03105ntm a22003977 4500 001 1146565
005 20240812064646.5
006 m o d
007 cr bn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382785912
035 $a (MiAaPQ)AAI31302280
035 $a AAI31302280
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Chen, Bohan. $3 1471972
245 1 0 $a Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.
264 0 $c 2024
300 $a 1 online resource (225 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisor: Bertozzi, Andrea L.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2024.
504 $a Includes bibliographical references
520 $a Graph-based machine learning is a powerful framework for analyzing and understanding complex data structures in various domains. This thesis introduces novel graph-based methods in multiple image analysis tasks, including classification, segmentation, and unmixing, as well as their application in enhancing large language models. The key contributions include: (1) the development of new core-set selection and batch active learning methods that significantly improve the efficiency of graph-based active learning while maintaining its effectiveness; (2) the integration of graph learning, active learning, and advanced feature embedding methods to construct pipelines for SAR image classification and multi- or hyperspectral image segmentation, outperforming neural network-based classifiers or segmenters in semi-supervised learning tasks with limited training data; (3) the incorporation of graph-based regularization into the optimization problem of hyperspectral unmixing, enabling the utilization of a small amount of labeled pixels to greatly improve the performance compared to blind unmixing; and (4) the extension of graph Laplacian-based methods to automatically construct knowledge graphs in combination with large language models, enhancing their information retrieval and response generation capabilities.The proposed methods showcase the effectiveness and versatility of graph-based approaches in addressing challenges such as limited labeled data, computational efficiency, and knowledge representation. The thesis demonstrates the potential of graph-based methods in pushing the boundaries of image and document analysis and their applicability in a wide range of machine learning problems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Applied mathematics. $3 1069907
650 4 $a Remote sensing. $3 557272
653 $a Active learning
653 $a Document analysis
653 $a Graph theory
653 $a Hyperspectral imaging
653 $a Image analysis
655 7 $a Electronic books. $2 local $3 554714
690 $a 0364
690 $a 0800
690 $a 0799
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Los Angeles. $b Mathematics 0540. $3 1180777
773 0 $t Dissertations Abstracts International $g 85-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31302280 $z click for full text (PQDT)