Skip to Main content Skip to Navigation
Conference papers

TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation

Matthieu Guillaumin 1 Thomas Mensink 1 Jakob Verbeek 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Image auto-annotation is an important open problem in computer vision. For this task we propose TagProp, a discriminatively trained nearest neighbor model. Tags of test images are predicted using a weighted nearest-neighbor model to exploit labeled training images. Neighbor weights are based on neighbor rank or distance. TagProp allows the integration of metric learning by directly maximizing the log-likelihood of the tag predictions in the training set. In this manner, we can optimally combine a collection of image similarity metrics that cover different aspects of image content, such as local shape descriptors, or global color histograms. We also introduce a word specific sigmoidal modulation of the weighted neighbor tag predictions to boost the recall of rare words. We investigate the performance of different variants of our model and compare to existing work. We present experimental results for three challenging data sets. On all three, TagProp makes a marked improvement as compared to the current state-of-the-art.
Document type :
Conference papers
Complete list of metadata

Cited literature [5 references]  Display  Hide  Download
Contributor : Thoth Team Connect in order to contact the contributor
Submitted on : Thursday, December 2, 2010 - 1:50:06 PM
Last modification on : Tuesday, October 19, 2021 - 11:13:04 PM
Long-term archiving on: : Monday, November 5, 2012 - 11:05:29 AM





Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid. TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation. ICCV 2009 - 12th International Conference on Computer Vision, Sep 2009, Kyoto, Japan. pp.309-316, ⟨10.1109/ICCV.2009.5459266⟩. ⟨inria-00439276⟩



Record views


Files downloads