Label-Embedding for Image Classification

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.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [70 references]  Display  Hide  Download
Contributor : Thoth Team <>
Submitted on : Wednesday, September 30, 2015 - 11:31:35 AM
Last modification on : Tuesday, February 12, 2019 - 10:30:06 AM
Document(s) archivé(s) le : Thursday, December 31, 2015 - 10:23:20 AM


Files produced by the author(s)




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⟩



Record views


Files downloads