| HAL-Inria | Publications, software ... of Inria's scientists |
Attribute-Based Classification with Label-Embedding
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.
Cited literature [12 references]
https://hal.inria.fr/hal-00903502
Contributor : Thoth Team <>
Submitted on : Tuesday, November 12, 2013 - 12:22:23 PM
Last modification on : Thursday, March 26, 2020 - 8:49:26 PM
Document(s) archivé(s) le : Thursday, February 13, 2014 - 12:11:07 PM
Contributor : Thoth Team <>
Submitted on : Tuesday, November 12, 2013 - 12:22:23 PM
Last modification on : Thursday, March 26, 2020 - 8:49:26 PM
Document(s) archivé(s) le : Thursday, February 13, 2014 - 12:11:07 PM
Files
orl2013_submission_1.pdf
Files produced by the author(s)