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

Maxime Bucher 1, 2 Stéphane Herbin 1 Frédéric Jurie 2
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.
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download
Contributor : Maxime Bucher <>
Submitted on : Monday, July 25, 2016 - 5:40:51 PM
Last modification on : Tuesday, April 2, 2019 - 1:35:53 AM


Files produced by the author(s)


  • HAL Id : hal-01348827, version 1
  • ARXIV : 1603.02644


Maxime Bucher, Stéphane Herbin, Frédéric Jurie. Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification. ECCV 2016, Oct 2016, amsterdam, Netherlands. ⟨hal-01348827⟩



Record views


Files downloads