Multimodal semi-supervised learning for image classification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Multimodal semi-supervised learning for image classification

Matthieu Guillaumin
  • Fonction : Auteur
  • PersonId : 879978
Jakob Verbeek
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

In image categorization the goal is to decide if an image belongs to a certain category or not. A binary classifier can be learned from manually labeled images; while using more labeled examples improves performance, obtaining the image labels is a time consuming process. We are interested in how other sources of information can aid the learning process given a fixed amount of labeled images. In particular, we consider a scenario where keywords are associated with the training images, eg as found on photo sharing websites. The goal is to learn a classifier for images alone, but we will use the keywords associated with labeled and unlabeled images to improve the classifier using semi-supervised learning. We first learn a strong Multiple Kernel Learning (MKL) classifier using both the image content and keywords, and use it to score unlabeled images. We then learn classifiers on visual features only, either support vector machines (SVM) or least-squares regression (LSR), from the MKL output values on both the labeled and unlabeled images. In our experiments on 20 classes from the PASCAL VOC'07 set and 38 from the MIR Flickr set, we demonstrate the benefit of our semi-supervised approach over only using the labeled images. We also present results for a scenario where we do not use any manual labeling but directly learn classifiers from the image tags. The semi-supervised approach also improves classification accuracy in this case.
Fichier principal
Vignette du fichier
GVS10.pdf (602.64 Ko) Télécharger le fichier
Vignette du fichier
GVS10.png (726.45 Ko) Télécharger le fichier
slides.pdf (3.25 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre

Dates et versions

inria-00548640 , version 1 (20-12-2010)

Identifiants

Citer

Matthieu Guillaumin, Jakob Verbeek, Cordelia Schmid. Multimodal semi-supervised learning for image classification. CVPR 2010 - 23rd IEEE Conference on Computer Vision & Pattern Recognition, Jun 2010, San Francisco, United States. pp.902-909, ⟨10.1109/CVPR.2010.5540120⟩. ⟨inria-00548640⟩
871 Consultations
4049 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More