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
https://hal.inria.fr/hal-00903502
Contributeur : Thoth Team
<>
Soumis le : mardi 12 novembre 2013 - 12:22:23
Dernière modification le : lundi 17 décembre 2018 - 11:22:02
Document(s) archivé(s) le : jeudi 13 février 2014 - 12:11:07
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〉
