Label-Embedding for Image Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Pattern Analysis and Machine Intelligence Year : 2016

Label-Embedding for Image Classification


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.
Fichier principal
Vignette du fichier
TPAMI.pdf (7.75 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01207145 , version 1 (30-09-2015)



Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid. Label-Embedding for Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38 (7), pp.1425-1438. ⟨10.1109/TPAMI.2015.2487986⟩. ⟨hal-01207145⟩
852 View
918 Download



Gmail Facebook X LinkedIn More