Learning Visual Similarity Measures for Comparing Never Seen Objects - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Learning Visual Similarity Measures for Comparing Never Seen Objects

Eric Nowak
  • Fonction : Auteur
Frédéric Jurie

Résumé

In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled "same" or "different". This is far less informative than the commonly used individual image labels (e.g. "car model X"), but it is cheaper to obtain. The proposed algorithm learns the characteristic differences between local descriptors sampled from pairs of "same" and "different" images. These differences are vector quantized by an ensemble of extremely randomized binary trees, and the similarity measure is computed from the quantized differences. The extremely randomized trees are fast to learn, robust due to the redundant information they carry and they have been proved to be very good clusterers. Furthermore, the trees efciently combine different feature types (SIFT and geometry). We evaluate our innovative similarity measure on four very different datasets and consistantly outperform the state-of-the-art competitive approaches.
Fichier principal
Vignette du fichier
NJ07.pdf (1.32 Mo) Télécharger le fichier
nowak_jurie_cvpr07_slides.pdf (2.91 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Format : Autre

Dates et versions

hal-00203958 , version 1 (14-01-2008)

Identifiants

Citer

Eric Nowak, Frédéric Jurie. Learning Visual Similarity Measures for Comparing Never Seen Objects. CPVR 2007 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.382969⟩. ⟨hal-00203958⟩
453 Consultations
915 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More