Speaker
Dr
Stefano Cavuoti
(INAF - Astronomical Observatory of Capodimonte Napoli)
Description
This presentation explores some applications of transfer learning in astronomical image analysis, focusing on the usage of a pretrained network (EfficientNet) as a feature extractor. We discuss methods for identifying active galactic nuclei, extracting physical parameters, and detecting anomalies in time series data. Additionally, we present some potential future applications, demonstrating the versatility of this approach, even without a training phase.
Primary author
Dr
Stefano Cavuoti
(INAF - Astronomical Observatory of Capodimonte Napoli)
Co-authors
Dr
Demetra De Cicco
(University of Napoli “Federico II”)
Mr
Lars Doorenbos
(AIMI, ARTORG Center, University of Bern)
Mr
Gianluca Sasanelli
(University of Napoli “Federico II”)
Dr
Olena Torbaniuk
(University of Bologna)
Prof.
Massimo Brescia
(University of Napoli “Federico II”)
Prof.
Giuseppe Longo
(University of Napoli “Federico II”)
Dr
Pablo Márquez-Neila
(AIMI, ARTORG Center, University of Bern)
Prof.
Maurizio Paolillo
(University of Napoli “Federico II”)
Prof.
Raphael Sznitman
(AIMI, ARTORG Center, University of Bern)
Dr
Crescenzo Tortora
(INAF - Astronomical Observatory of Capodimonte Napoli)
