[Paper] Visual Instance Retrieval with Deep Convolutional Networks

This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local featu...

Full description

Saved in:
Bibliographic Details
Published inITE TRANSACTIONS ON MEDIA TECHNOLOGY AND APPLICATIONS Vol. 4; no. 3; pp. 251 - 258
Main Authors Razavian, Ali S., Sullivan, Josephine, Carlsson, Stefan, Maki, Atsuto
Format Journal Article
LanguageEnglish
Published 2016
Subjects
Convolutional network
Learning representation
Multi-resolution search
Visual instance retrieval
Online AccessGet full text

Cover

More Information
Summary:This paper provides an extensive study on the availability of image representations based on convolutional networks (ConvNets) for the task of visual instance retrieval. Besides the choice of convolutional layers, we present an efficient pipeline exploiting multi-scale schemes to extract local features, in particular, by taking geometric invariance into explicit account, i.e. positions, scales and spatial consistency. In our experiments using five standard image retrieval datasets, we demonstrate that generic ConvNet image representations can outperform other state-of-the-art methods if they are extracted appropriately.
ISSN:2186-7364
2186-7364
DOI:10.3169/mta.4.251