University of AmsterdamUniversity of AmsterdamUvA

  • Terms of use
  • Contact

UvA-DARE (Digital Academic Repository)

  • Home
  • Advanced Search
  • Browse
  • My selection

Search UvA-DARE

Author
E. Gavves
T. Mensink
T. Tommasi
C.G.M. Snoek
T. Tuytelaars
Year
2015
Title
Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
Event
ICCV 2015: IEEE International Conference on Computer Vision
Book/source title
Proceedings: 2015 IEEE International Conference on Computer Vision: 11-18 December 2015, Santiago, Chile
Pages (from-to)
2731-2739
Publisher
Los Alamitos, CA: IEEE Computer Society
ISBN
9781467383905
Document type
Conference contribution
Faculty
Faculty of Science (FNWI)
Institute
Informatics Institute (IVI)
Abstract
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data? In this work we make a first contribution to answer this question in the context of image classification. We frame this quest as an active learning problem and use zero-shot classifiers to guide the learning process by linking the new task to the the existing classifiers. By revisiting the dual formulation of adaptive SVM, we reveal two basic conditions to choose greedily only the most relevant samples to be annotated. On this basis we propose an effective active learning algorithm which learns the best possible target classification model with minimum human labeling effort. Extensive experiments on two challenging datasets show the value of our approach compared to the state-of-the-art active learning methodologies, as well as its potential to reuse past datasets with minimal effort for future tasks.
URL
go to publisher's site
Language
English
Permalink
http://hdl.handle.net/11245/1.488890
Downloads
  • GavvesICCV2015

Disclaimer/Complaints regulations

If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library, or send a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible.

PrintPrint this pageShareShare via emailShare on facebookShare on linkedinShare on twitter
  • University library
  • About UvA-DARE
  • Disclaimer
Copyright UvA 2014