Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification

Maxime Bucher 1 Frédéric Jurie 2 Stéphane Herbin 1
2 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images – one of the main ingredients of zero-shot learning – by formulating it as a metric learning problem. The optimized empirical criterion associates two types of sub-task constraints: metric discriminating capacity and accurate attribute prediction. This results in a novel expression of zero-shot learning not requiring the notion of class in the training phase: only pairs of image/attributes, augmented with a consistency indicator, are given as ground truth. At test time, the learned model can predict the consistency of a test image with a given set of attributes , allowing flexible ways to produce recognition inferences. Despite its simplicity, the proposed approach gives state-of-the-art results on four challenging datasets used for zero-shot recognition evaluation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [47 references]  Display  Hide  Download
Contributor : Ccsd Sciencesconf.Org <>
Submitted on : Monday, September 3, 2018 - 3:00:34 PM
Last modification on : Tuesday, April 2, 2019 - 1:35:54 AM
Long-term archiving on : Tuesday, December 4, 2018 - 2:46:09 PM


Files produced by the author(s)


  • HAL Id : hal-01866628, version 1


Maxime Bucher, Frédéric Jurie, Stéphane Herbin. Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification. ORASIS 2017, GREYC, Jun 2017, Colleville-sur-Mer, France. ⟨hal-01866628⟩



Record views


Files downloads