Can Generalised Divergences Help for Invariant Neural Networks? - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2023

Can Generalised Divergences Help for Invariant Neural Networks?

Résumé

We consider a framework including multiple augmentation regularisation by generalised divergences to induce invariance for nongroup transformations during training of convolutional neural networks. Experiments on supervised classification of images at different scales not considered during training illustrate that our proposed method performs better than classical data augmentation.
Fichier principal
Vignette du fichier
GSI-168.pdf (673.81 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04303522 , version 1 (23-11-2023)
hal-04303522 , version 2 (08-07-2024)

Identifiants

Citer

Santiago Velasco-Forero. Can Generalised Divergences Help for Invariant Neural Networks?. Geometric Science of Information, 14071, Springer Nature Switzerland, pp.82-90, 2023, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-38271-0_9⟩. ⟨hal-04303522v2⟩
12 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More