liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Learning Local Descriptors by Optimizing the Keypoint-Correspondence Criterion: Applications to Face Matching, Learning From Unlabeled Videos and 3D-Shape Retrieval
Univ Zagreb, Croatia.
Univ Zagreb, Croatia.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-6763-5487
2019 (English)In: IEEE Transactions on Image Processing, ISSN 1057-7149, E-ISSN 1941-0042, Vol. 28, no 1, p. 279-290Article in journal (Refereed) Published
Abstract [en]

Current best local descriptors are learned on a large data set of matching and non-matching keypoint pairs. However, data of this kind are not always available, since the detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We describe an end-to-end differentiable architecture that enables the learning of local keypoint descriptors from such weakly labeled data. In addition, we discuss how to improve the method by incorporating the procedure of mining hard negatives. We also show how our approach can be used to learn convolutional features from unlabeled video signals and 3D models.

Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2019. Vol. 28, no 1, p. 279-290
Keywords [en]
Image matching; distance learning; multi-layer neural network; local descriptors
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-151931DOI: 10.1109/TIP.2018.2867270ISI: 000445364000022PubMedID: 30235113OAI: oai:DiVA.org:liu-151931DiVA, id: diva2:1256386
Note

Funding Agencies|Visage Technologies AB, Linkoping, Sweden; Croatian Science Foundation [8065]

Available from: 2018-10-16 Created: 2018-10-16 Last updated: 2019-03-18

Open Access in DiVA

fulltext(3934 kB)67 downloads
File information
File name FULLTEXT01.pdfFile size 3934 kBChecksum SHA-512
66265cd74e298603e825103dbd0c81c8ca9debad24e9f8e7c78ea47e7469127345d72254828ee0ddf29e1092d4bb0141d152d3561e3c6a6ae4400eaefca14d76
Type fulltextMimetype application/pdf

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Ahlberg, Jörgen
By organisation
Computer VisionFaculty of Science & Engineering
In the same journal
IEEE Transactions on Image Processing
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 67 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
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 3256 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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