FULLY TRAINABLE GAUSSIAN DERIVATIVE CONVOLUTIONAL LAYER - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

FULLY TRAINABLE GAUSSIAN DERIVATIVE CONVOLUTIONAL LAYER

Valentin Penaud--Polge
  • Fonction : Auteur
  • PersonId : 1149801
Jesus Angulo

Résumé

The Gaussian kernel and its derivatives have already been employed for Convolutional Neural Networks in several previous works. Most of these papers proposed to compute filters by linearly combining one or several bases of fixed or slightly trainable Gaussian kernels with or without their derivatives. In this article, we propose a high-level configurable layer based on anisotropic, oriented and shifted Gaussian derivative kernels which generalize notions encountered in previous related works while keeping their main advantage. The results show that the proposed layer has competitive performance compared to previous works and that it can be successfully included in common deep architectures such as VGG16 for image classification and U-net for image segmentation.
Fichier principal
Vignette du fichier
main.pdf (514.13 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03722767 , version 1 (13-07-2022)

Identifiants

Citer

Valentin Penaud--Polge, Santiago Velasco-Forero, Jesus Angulo. FULLY TRAINABLE GAUSSIAN DERIVATIVE CONVOLUTIONAL LAYER. 29th IEEE International Conference on Image Processing (IEEE ICIP), Oct 2022, Bordeaux, France. ⟨hal-03722767⟩
61 Consultations
106 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More