東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Exploring the Frontier of Graph-base...

Chen, Bohan.

FindBook

Google Book

Amazon

博客來

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

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Exploring the Frontier of Graph-based Approaches for Image and Document Analysis./
作者:	Chen, Bohan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2024,
面頁冊數:	225 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Applied mathematics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31302280
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. - Ann Arbor : ProQuest Dissertations & Theses, 2024 - 225 p.

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

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

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.

ISBN: 9798382785912Subjects--Topical Terms:

2122814
Applied mathematics.
Subjects--Index Terms:

Active learning

Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.
LDR:02883nmm a2200385 4500 001 2398469
005 20240812064646.5
006 m o d
007 cr#unu||||||||
008 251215s2024 ||||||||||||||||| ||eng d
020 $a 9798382785912
035 $a (MiAaPQ)AAI31302280
035 $a AAI31302280
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chen, Bohan. $3 3768382
245 1 0 $a Exploring the Frontier of Graph-based Approaches for Image and Document Analysis.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 225 p.
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.
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.
590 $a School code: 0031.
650 4 $a Applied mathematics. $3 2122814
650 4 $a Remote sensing. $3 535394
653 $a Active learning
653 $a Document analysis
653 $a Graph theory
653 $a Hyperspectral imaging
653 $a Image analysis
690 $a 0364
690 $a 0800
690 $a 0799
710 2 $a University of California, Los Angeles. $b Mathematics 0540. $3 2096468
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0031
791 $a Ph.D.
792 $a 2024
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31302280