Fine-tuning Convolutional Neural Networks: a comprehensive guide and benchmark analysis for Glaucoma Screening - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Fine-tuning Convolutional Neural Networks: a comprehensive guide and benchmark analysis for Glaucoma Screening

Amed Mvoulana
  • Fonction : Auteur
  • PersonId : 1054683
Rostom Kachouri
Mohamed Akil

Résumé

This work aimed at giving a comprehensive, indetailed and benchmark guide on the route to fine-tuning Convolutional Neural Networks (CNNs) for glaucoma screening. Transfer learning consists in a promising alternative to train CNNs from scratch, to avoid the huge data and resources requirements. After a thorough study of five state-of-the-art CNNs architectures, a complete and well-explained strategy for fine-tuning these networks is proposed, using hyperparameter grid-searching and two-phase training approach. Excellent performance is reached on model evaluation, with a 0.9772 AUROC validation rate, giving arise to reliable glaucoma diagnosis-help systems. Also, a baseline benchmark analysis is conducted, studying the models according to performance indices such as model complexity and size, AUROC density and inference time. This in-depth analysis allows a rigorous comparison between model characteristics, and is useful for giving practioners important trademarks for prospective applications and deployments.
Fichier principal
Vignette du fichier
root.pdf (14.32 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03205034 , version 1 (22-04-2021)

Identifiants

  • HAL Id : hal-03205034 , version 1

Citer

Amed Mvoulana, Rostom Kachouri, Mohamed Akil. Fine-tuning Convolutional Neural Networks: a comprehensive guide and benchmark analysis for Glaucoma Screening. 25th International Conference in Pattern Recognition, Jan 2021, Milano (on line), Italy. ⟨hal-03205034⟩
61 Consultations
113 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More