| HAL-Inria | Publications, software ... of Inria's scientists |
Label-Embedding for Attribute-Based Classification
Abstract : Attributes are an intermediate representation, which enables 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 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. The label embedding framework offers other advantages such as the ability to leverage alternative sources of information in addition to attributes (e.g. class hierarchies) or to transition smoothly from zero-shot learning to learning with large quantities of data.
Cited literature [43 references]
https://hal.inria.fr/hal-00815747
Contributor : Thoth Team <>
Submitted on : Thursday, July 11, 2013 - 7:14:24 PM
Last modification on : Thursday, March 26, 2020 - 8:49:28 PM
Document(s) archivé(s) le : Wednesday, April 5, 2017 - 10:07:05 AM
Contributor : Thoth Team <>
Submitted on : Thursday, July 11, 2013 - 7:14:24 PM
Last modification on : Thursday, March 26, 2020 - 8:49:28 PM
Document(s) archivé(s) le : Wednesday, April 5, 2017 - 10:07:05 AM
Files
PID2749989.pdf
Files produced by the author(s)