CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00303799" target="_blank" >RIV/68407700:21230/16:00303799 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/~radenfil/publications/Radenovic-ECCV16.pdf" target="_blank" >http://cmp.felk.cvut.cz/~radenfil/publications/Radenovic-ECCV16.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-46448-0_1" target="_blank" >10.1007/978-3-319-46448-0_1</a>
Alternative languages
Result language
angličtina
Original language name
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
Original language description
Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/LL1303" target="_blank" >LL1303: Large Scale Category Retrieval</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I
ISBN
978-3-319-46447-3
ISSN
0302-9743
e-ISSN
—
Number of pages
18
Pages from-to
3-20
Publisher name
Springer
Place of publication
—
Event location
Amsterdam
Event date
Oct 8, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000389382700001