DIABLO: Dictionary-based attention block for deep metric learning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Letters Année : 2020

DIABLO: Dictionary-based attention block for deep metric learning

Pierre Jacob
Edouard Klein
  • Fonction : Auteur
  • PersonId : 901877

Résumé

Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation. In this paper, we propose DIABLO, a dictionary-based attention method for image embedding. DIABLO produces richer representations by aggregating only visually-related features together while being easier to train than other attention-based methods in deep metric learning. This is experimentally confirmed on four deep metric learning datasets (Cub-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval) for which DIABLO shows state-of-the-art performances.
Fichier principal
Vignette du fichier
S0167865520300982.pdf (342.09 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02510473 , version 1 (22-08-2022)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Pierre Jacob, David Picard, Aymeric Histace, Edouard Klein. DIABLO: Dictionary-based attention block for deep metric learning. Pattern Recognition Letters, 2020, ⟨10.1016/j.patrec.2020.03.020⟩. ⟨hal-02510473⟩
179 Consultations
18 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More