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

Towards Large-Scale and Fine-Grained...

Zhang, Xiaofan.

FindBook

Google Book

Amazon

博客來

Towards Large-Scale and Fine-Grained Image Recognition.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Towards Large-Scale and Fine-Grained Image Recognition./
作者:	Zhang, Xiaofan.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	113 p.
附註:	Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
Contained By:	Dissertation Abstracts International79-04B(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10636942
ISBN:	9780355440782

Towards Large-Scale and Fine-Grained Image Recognition.
Zhang, Xiaofan.

Towards Large-Scale and Fine-Grained Image Recognition. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 113 p.

Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.

Thesis (Ph.D.)--The University of North Carolina at Charlotte, 2017.

In this dissertation, we aim to investigate the problem of large-scale and fine-grained image recognition, which focuses on the differentiation of subtle differences among subordinate classes and a large number of images. Particularly, we tackle this problem by answering three inter-related questions: 1) how to learn robust and invariant feature representations that can differentiate subtle and fine-grained differences among subordinate classes, 2) how to index these features for efficient image analysis (e.g., classification, content-based retrieval) at a large scale, and 3) how to fuse different type of features to get better results. We propose a series of methods to solve these three problems. Regarding feature representation learning, we design an architecture of convolutional neural networks (CNNs), by unifying the classification constraint and the similarity constraint in a multi-learning framework. Also, structured labels are embedded in this framework, so the similarity of images can be defined at different levels of relevance, e.g., the number of shared attributes, through learned feature representations. Regarding feature indexing, we propose multiple methods based on hashing and binary coding, enabling real-time image retrieval and classification for high-dimensional features and/or a large number of features. Regarding feature fusion, we employ a graph-based query-specific fusion approach where multiple retrieval results (i.e., rank lists) are integrated and reordered based on a fused graph. We have evaluated these methods on both natural images and medical images, as we advocate that medical image recognition (e.g., cancer grading by histopathological images) needs ultra-fine-grained differentiation. The experimental results demonstrate the efficacy of our methods, in terms of both accuracy and efficiency.

ISBN: 9780355440782Subjects--Topical Terms:

523869
Computer science.

Towards Large-Scale and Fine-Grained Image Recognition.
LDR:02776nmm a2200289 4500 001 2156483
005 20180517112612.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355440782
035 $a (MiAaPQ)AAI10636942
035 $a (MiAaPQ)uncc:11529
035 $a AAI10636942
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Xiaofan. $3 3178175
245 1 0 $a Towards Large-Scale and Fine-Grained Image Recognition.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 113 p.
500 $a Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
500 $a Adviser: Shaoting Zhang.
502 $a Thesis (Ph.D.)--The University of North Carolina at Charlotte, 2017.
520 $a In this dissertation, we aim to investigate the problem of large-scale and fine-grained image recognition, which focuses on the differentiation of subtle differences among subordinate classes and a large number of images. Particularly, we tackle this problem by answering three inter-related questions: 1) how to learn robust and invariant feature representations that can differentiate subtle and fine-grained differences among subordinate classes, 2) how to index these features for efficient image analysis (e.g., classification, content-based retrieval) at a large scale, and 3) how to fuse different type of features to get better results. We propose a series of methods to solve these three problems. Regarding feature representation learning, we design an architecture of convolutional neural networks (CNNs), by unifying the classification constraint and the similarity constraint in a multi-learning framework. Also, structured labels are embedded in this framework, so the similarity of images can be defined at different levels of relevance, e.g., the number of shared attributes, through learned feature representations. Regarding feature indexing, we propose multiple methods based on hashing and binary coding, enabling real-time image retrieval and classification for high-dimensional features and/or a large number of features. Regarding feature fusion, we employ a graph-based query-specific fusion approach where multiple retrieval results (i.e., rank lists) are integrated and reordered based on a fused graph. We have evaluated these methods on both natural images and medical images, as we advocate that medical image recognition (e.g., cancer grading by histopathological images) needs ultra-fine-grained differentiation. The experimental results demonstrate the efficacy of our methods, in terms of both accuracy and efficiency.
590 $a School code: 0694.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a The University of North Carolina at Charlotte. $b Computer Science. $3 3181506
773 0 $t Dissertation Abstracts International $g 79-04B(E).
790 $a 0694
791 $a Ph.D.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10636942