Attribute-Based Classification with Label-Embedding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Attribute-Based Classification with Label-Embedding


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.
Fichier principal
Vignette du fichier
orl2013_submission_1.pdf (158.83 Ko) Télécharger le fichier
Vignette du fichier
ORL_2013.png (210.72 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00903502 , version 1 (12-11-2013)


  • 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, Neural Information Processing Systems (NIPS) Foundation, Dec 2013, Lake Tahoe, United States. ⟨hal-00903502⟩
839 View
657 Download


Gmail Facebook Twitter LinkedIn More