Enriching synthetic data with real noise using Neural Style Transfer

Deep Learning experiments require large amounts of labeled data, but few annotated seismic datasets are available and annotation is a time-consuming, expensive activity. Synthetic modeled datasets may be a viable alternative. However, they lack the variability and intricacies of a real data signal....

Full description

Bibliographic Details

Main Authors:	Takemoto, Naomi, Coimbra, Tiago, Araújo, Lucas, Tygel, Martin, Avila, Sandra, Borin, Edson
Format:	Online
Language:	Portuguese
Published:	Universidade Estadual de Campinas 2019
Subjects:	Machine learning Geophysics Neural style transfer
Online Access:	https://econtents.sbu.unicamp.br/eventos/index.php/pibic/article/view/2342
Tags:	Add Tag No Tags, Be the first to tag this record!