Presentation 2018-03-18
Image Retrieval with Augmented Fine-tuned CNN Features
Zhao Longjiao, Yu Wang, Jien Kato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, pre-trained CNN features have shown a good performance on the content-based image retrieval task. In this paper, we study two strategies that are expected to bring further improvement to CNN features: feature augmentation, and network fine-tuning. Specifically, we study a feature augmentation method, 3 fine-tuning settings, and their combinations on the popular Oxford building and Paris datasets. We confirmed both strategies lead to better image retrieval performance, and their combination leads to even further improvements.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image retrievalfine-tuneaugmentation
Paper # BioX2017-55,PRMU2017-191
Date of Issue 2018-03-11 (BioX, PRMU)

Conference Information
Committee PRMU / BioX
Conference Date 2018/3/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII) / Kazuhiko Sumi(AGU)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Hiroshi Takano(Toyama Pref. Univ.) / Hitoshi Imaoka(NEC)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Hiroshi Takano(Shizuoka Univ.) / Hitoshi Imaoka(Fujitsu Labs.)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Norihiro Okui(KDDI Research)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Retrieval with Augmented Fine-tuned CNN Features
Sub Title (in English)
Keyword(1) image retrievalfine-tuneaugmentation
1st Author's Name Zhao Longjiao
1st Author's Affiliation Nagoya University(Nagoya Univ.)
2nd Author's Name Yu Wang
2nd Author's Affiliation Nagoya University(Nagoya Univ.)
3rd Author's Name Jien Kato
3rd Author's Affiliation Nagoya University(Nagoya Univ.)
Date 2018-03-18
Paper # BioX2017-55,PRMU2017-191
Volume (vol) vol.117
Number (no) BioX-513,PRMU-514
Page pp.pp.115-119(BioX), pp.115-119(PRMU),
#Pages 5
Date of Issue 2018-03-11 (BioX, PRMU)