A Small-Scale Network for Seismic Patterns Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A Small-Scale Network for Seismic Patterns Classification

Résumé

Deep Convolutional Neural Networks (DCNNs) correspond to the state-of-art for image classification. However to train such systems it is necessary to have access to a large number of samples and powerful computational resources, given the huge number of involved parameters. In the field of seismic images, large and freely available databases are scarce due to their strategic interest. In this situation, large architectures lead to hardly tractable problems in terms of overfitting. In this paper, we propose a reduced-size CNN with low computational cost that allows high accuracy performance on two small seismic datasets. The results are compared with KNN, SVM and LeNet.
Fichier non déposé

Dates et versions

hal-03619395 , version 1 (25-03-2022)

Identifiants

Citer

Monacer da Silva, Jean Charléty, Aurélia Fraysse, Jean-Christophe Pesquet. A Small-Scale Network for Seismic Patterns Classification. 28th European Signal Processing Conference (EUSIPCO 2020), Jan 2021, Amsterdam, Netherlands. ⟨10.23919/Eusipco47968.2020.9287853⟩. ⟨hal-03619395⟩
34 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More