Label-Embedding for Image Classification

Zeynep Akata 1, 2 Florent Perronnin 2 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Attributes act as intermediate representations that 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 that 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 classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. Label embedding enjoys a built-in ability to leverage alternative sources of information instead of or in addition to attributes, such as e.g. class hierarchies or textual descriptions. Moreover, label embedding encompasses the whole range of learning settings from zero-shot learning to regular learning with a large number of labeled examples.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (7), pp.1425-1438. <10.1109/TPAMI.2015.2487986>
Liste complète des métadonnées


https://hal.inria.fr/hal-01207145
Contributeur : Thoth Team <>
Soumis le : mercredi 30 septembre 2015 - 11:31:35
Dernière modification le : jeudi 12 janvier 2017 - 19:40:19
Document(s) archivé(s) le : jeudi 31 décembre 2015 - 10:23:20

Fichier

TPAMI.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid. Label-Embedding for Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2016, 38 (7), pp.1425-1438. <10.1109/TPAMI.2015.2487986>. <hal-01207145>

Partager

Métriques

Consultations de
la notice

659

Téléchargements du document

516