國立虎尾科技大學 |

Towards Large-Scale and Fine-Grained Image Recognition.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Towards Large-Scale and Fine-Grained Image Recognition./
作者:	Zhang, Xiaofan.
面頁冊數:	1 online resource (113 pages)
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:	click for full text (PQDT)
ISBN:	9780355440782

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

Towards Large-Scale and Fine-Grained Image Recognition. - 1 online resource (113 pages)

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

Thesis (Ph.D.)

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355440782Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Towards Large-Scale and Fine-Grained Image Recognition.
LDR:03113ntm a2200337Ki 4500 001 910844
005 20180517112612.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355440782
035 $a (MiAaPQ)AAI10636942
035 $a (MiAaPQ)uncc:11529
035 $a AAI10636942
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Zhang, Xiaofan. $3 1182327
245 1 0 $a Towards Large-Scale and Fine-Grained Image Recognition.
264 0 $c 2017
300 $a 1 online resource (113 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: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
500 $a Adviser: Shaoting Zhang.
502 $a Thesis (Ph.D.) $c The University of North Carolina at Charlotte $d 2017.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of North Carolina at Charlotte. $b Computer Science. $3 1182328
773 0 $t Dissertation Abstracts International $g 79-04B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10636942 $z click for full text (PQDT)