Attribute-Based Classification with Label-Embedding

Zeynep Akata 1, 2, * Florent Perronnin 1 Zaid Harchaoui 2 Cordelia Schmid 2
* Auteur correspondant
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Attributes are an intermediate representation whose purpose is to enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function which measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct class has a higher compatibility than the incorrect ones. Experimental results on two standard image classification datasets are presented, resp. on the Animals With Attributes and on Caltech-UCSD-Birds datasets.
Type de document :
Communication dans un congrès
NIPS 2013 Workshop on Output Representation Learning, Dec 2013, Lake Tahoe, United States. 2013
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger
Contributeur : Thoth Team <>
Soumis le : mardi 12 novembre 2013 - 12:22:23
Dernière modification le : mardi 12 février 2019 - 10:30:05
Document(s) archivé(s) le : jeudi 13 février 2014 - 12:11:07


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00903502, version 1



Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid. Attribute-Based Classification with Label-Embedding. NIPS 2013 Workshop on Output Representation Learning, Dec 2013, Lake Tahoe, United States. 2013. 〈hal-00903502〉



Consultations de la notice


Téléchargements de fichiers