Attribute-Based Classification with Label-Embedding

Zeynep Akata; Florent Perronnin; Zaid Harchaoui; Cordelia Schmid

Attribute-Based Classification with Label-Embedding

Zeynep Akata ^{1, 2, *} Florent Perronnin ¹ Zaid Harchaoui ² Cordelia Schmid ²

* Corresponding author

1 Xerox Research Centre Europe [Meylan]

2 LEAR - Learning and recognition in vision

Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble

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.

Document type :

Conference papers

Domain :

Computer Science [cs] / Computer Vision and Pattern Recognition [cs.CV]

Complete list of metadatas

Cited literature [12 references] Display Hide Download

https://hal.inria.fr/hal-00903502
Contributor : Thoth Team <>
Submitted on : Tuesday, November 12, 2013 - 12:22:23 PM
Last modification on : Tuesday, February 12, 2019 - 10:30:05 AM
Long-term archiving on : Thursday, February 13, 2014 - 12:11:07 PM

orl2013_submission_1.pdf

Files produced by the author(s)

Attribute-Based Classification with Label-Embedding

Files

Identifiers

Collections

Citation

Export

Metrics

1331

932

Contact

Attribute-Based Classification with Label-Embedding

Files

Identifiers

Collections

Citation

Export

Share

Metrics

1331

932

Contact