Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

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

Résumé

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.
Fichier principal
Vignette du fichier
1_paper_1_.pdf (1018.47 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01866628 , version 1 (03-09-2018)

Identifiants

  • HAL Id : hal-01866628 , version 1

Citer

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⟩
83 Consultations
47 Téléchargements

Partager

Gmail Facebook X LinkedIn More