Discriminatively-learned global image representation using CNN as a local feature extractor for image retrieval

Wei Lin Ku, Hung Chun Chou, Wen-Hsiao Peng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

This work introduces an image retrieval framework based on using deep convolutional neural networks (CNN) as a local feature extractor. Motivated by the great success of CNN in recognition tasks, one may be tempted to simply adopt the output of CNN as a global image representation for retrieval. This straightforward approach, however, has proved deficient, because it can be vulnerable to various image transformation attacks. To address this issue, we propose to treat CNN as a local feature extractor, and a local image patch selection mechanism is developed to extract discriminative patches by observing their objectness responses, aspect ratios, relative scales, and locations in the image. The criterion is given by a learned posterior probability indicating how likely the image patch in question will find a correspondence in another similar image. In addition, the CNN's weight parameters are specifically adapted by a contrastive loss function to suit retrieval tasks. Extensive experiments on typical retrieval datasets confirm the superiority of the proposed scheme over the state-of-the-art methods.

Original languageEnglish
Title of host publication2015 Visual Communications and Image Processing, VCIP 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467373142
DOIs
StatePublished - 21 Apr 2016
EventVisual Communications and Image Processing, VCIP 2015 - Singapore, Singapore
Duration: 13 Dec 201516 Dec 2015

Publication series

Name2015 Visual Communications and Image Processing, VCIP 2015

Conference

ConferenceVisual Communications and Image Processing, VCIP 2015
CountrySingapore
CitySingapore
Period13/12/1516/12/15

Keywords

  • deep convolutional neural network
  • feature learning
  • image representation
  • image retrieval
  • object detection

Fingerprint Dive into the research topics of 'Discriminatively-learned global image representation using CNN as a local feature extractor for image retrieval'. Together they form a unique fingerprint.

Cite this