Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
From Generic to Specific Deep Representations for Visual Recognition
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. (Computer Vision)ORCID iD: 0000-0001-5211-6388
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0002-4266-6746
Show others and affiliations
2015 (English)In: Proceedings of CVPR 2015, IEEE conference proceedings, 2015Conference paper, Published paper (Refereed)
Abstract [en]

Evidence is mounting that ConvNets are the best representation learning method for recognition. In the common scenario, a ConvNet is trained on a large labeled dataset and the feed-forward units activation, at a certain layer of the network, is used as a generic representation of an input image. Recent studies have shown this form of representation to be astoundingly effective for a wide range of recognition tasks. This paper thoroughly investigates the transferability of such representations w.r.t. several factors. It includes parameters for training the network such as its architecture and parameters of feature extraction. We further show that different visual recognition tasks can be categorically ordered based on their distance from the source task. We then show interesting results indicating a clear correlation between the performance of tasks and their distance from the source task conditioned on proposed factors. Furthermore, by optimizing these factors, we achieve stateof-the-art performances on 16 visual recognition tasks.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015.
Series
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, ISSN 2160-7508
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-164527DOI: 10.1109/CVPRW.2015.7301270ISI: 000378887900005Scopus ID: 2-s2.0-84951960494ISBN: 978-146736759-2 (print)OAI: oai:DiVA.org:kth-164527DiVA: diva2:806070
Conference
CVPRW DeepVision Workshop,June 11, 2015, Boston, MA, USA
Note

QC 20150507

Available from: 2015-04-17 Created: 2015-04-17 Last updated: 2016-08-15Bibliographically approved

Open Access in DiVA

fulltext(533 kB)159 downloads
File information
File name FULLTEXT02.pdfFile size 533 kBChecksum SHA-512
32b0e8fa2ab69332df25dff56cb50748c3d0f0df16ebf081dc6f21547fa70ca024a0975c4f8616ff6d13ca951b6a0e3d645981c9f2720739abf97b4fdbd222e0
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusConference website

Authority records BETA

Azizpour, HosseinMaki, Atsuto

Search in DiVA

By author/editor
Azizpour, HosseinRazavian, Ali SharifSullivan, JosephineMaki, AtsutoCarlsson, Stefan
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 159 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 308 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf