Discriminatively-learned CNN Features for Image Retrieval

碩士 === 國立交通大學 === 資訊科學與工程研究所 === 103 === The thesis aims to learn discriminative features for image retrieval tasks based on using deep convolutional neural networks (CNN). Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN for retrieval....

Full description

Bibliographic Details
Main Authors:	Chou, Hung-Chun, 周宏春
Other Authors:	Tsai, Wen-Jiin
Format:	Others
Language:	zh-TW
Published:	2015
Online Access:	http://ndltd.ncl.edu.tw/handle/21952307307565825693

id	ndltd-TW-103NCTU5394158
record_format	oai_dc
spelling	ndltd-TW-103NCTU53941582017-09-06T04:22:12Z http://ndltd.ncl.edu.tw/handle/21952307307565825693 Discriminatively-learned CNN Features for Image Retrieval 針對影像搜尋應用中學習具鑑別能力之旋積類神經網路描述子 Chou, Hung-Chun 周宏春碩士國立交通大學資訊科學與工程研究所 103 The thesis aims to learn discriminative features for image retrieval tasks based on using deep convolutional neural networks (CNN). Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN for retrieval. However, CNN pre-trained model for classification tasks may not optimized for retrieval tasks. To address this issue, the CNN’s weight parameters are specifically adapted by a contrastive loss function to suit retrieval tasks. Extensive experiments conducted on typical retrieval datasets confirm the superiority of the proposed scheme over the state-of-the-art methods. Tsai, Wen-Jiin 蔡文錦 2015 學位論文 ; thesis 29 zh-TW
collection	NDLTD
language	zh-TW
format	Others
sources	NDLTD
description	碩士 === 國立交通大學 === 資訊科學與工程研究所 === 103 === The thesis aims to learn discriminative features for image retrieval tasks based on using deep convolutional neural networks (CNN). Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN for retrieval. However, CNN pre-trained model for classification tasks may not optimized for retrieval tasks. To address this issue, the CNN’s weight parameters are specifically adapted by a contrastive loss function to suit retrieval tasks. Extensive experiments conducted on typical retrieval datasets confirm the superiority of the proposed scheme over the state-of-the-art methods.
author2	Tsai, Wen-Jiin
author_facet	Tsai, Wen-Jiin Chou, Hung-Chun 周宏春
author	Chou, Hung-Chun 周宏春
spellingShingle	Chou, Hung-Chun 周宏春 Discriminatively-learned CNN Features for Image Retrieval
author_sort	Chou, Hung-Chun
title	Discriminatively-learned CNN Features for Image Retrieval
title_short	Discriminatively-learned CNN Features for Image Retrieval
title_full	Discriminatively-learned CNN Features for Image Retrieval
title_fullStr	Discriminatively-learned CNN Features for Image Retrieval
title_full_unstemmed	Discriminatively-learned CNN Features for Image Retrieval
title_sort	discriminatively-learned cnn features for image retrieval
publishDate	2015
url	http://ndltd.ncl.edu.tw/handle/21952307307565825693
work_keys_str_mv	AT chouhungchun discriminativelylearnedcnnfeaturesforimageretrieval AT zhōuhóngchūn discriminativelylearnedcnnfeaturesforimageretrieval AT chouhungchun zhēnduìyǐngxiàngsōuxúnyīngyòngzhōngxuéxíjùjiànbiénénglìzhīxuánjīlèishénjīngwǎnglùmiáoshùzi AT zhōuhóngchūn zhēnduìyǐngxiàngsōuxúnyīngyòngzhōngxuéxíjùjiànbiénénglìzhīxuánjīlèishénjīngwǎnglùmiáoshùzi
_version_	1718527019255332864

Discriminatively-learned CNN Features for Image Retrieval

Similar Items