IRIT & MISA at Image CLEF 2017 - Multi label classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

IRIT & MISA at Image CLEF 2017 - Multi label classification

Résumé

In this paper, we describe the participation of the Mami team at ImageCLEF 2017 for the Image Caption task. We participated to the concept detection subtask which aims at assigning a set of concept labels to a medical image. We used transfer learning method with VGG19 model for feature extraction to solve this task, and apply those features as input of a new neural network.
Fichier principal
Vignette du fichier
mothe_19083.pdf (129.91 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01913685 , version 1 (06-11-2018)

Identifiants

  • HAL Id : hal-01913685 , version 1
  • OATAO : 19083

Citer

Nomena Ny Hoavy, Josiane Mothe, Mamitiana Ignace Randrianarivony. IRIT & MISA at Image CLEF 2017 - Multi label classification. International Conference of the CLEF Association, CLEF 2017 Labs Working Notes (CLEF 2017), Sep 2017, Dublin, Ireland. pp. 1-6. ⟨hal-01913685⟩
85 Consultations
84 Téléchargements

Partager

Gmail Facebook X LinkedIn More