Deep Learning for Astronomical Object Classification: A Case Study

Author(s)

Martinazzo, Ana ; Espadoto, Mateus ; Hirata, Nina S. T. ; Farinella, GM ; Radeva, P ; Braz, J

• Document type: Journal article
• Source: VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP; v. N/A, p. 9-pg., 2020-01-01.

Abstract

With the emergence of photometric surveys in astronomy, came the challenge of processing and understanding an enormous amount of image data. In this paper, we systematically compare the performance of five popular ConvNet architectures when applied to three different image classification problems in astronomy to determine which architecture works best for each problem. We show that a VGG-style architecture pre-trained on ImageNet yields the best results on all studied problems, even when compared to architectures which perform much better on the ImageNet competition. (AU)

• FAPESP's process: 17/25835-9 - Understanding images and deep learning models
• Grantee: Nina Sumiko Tomita Hirata
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 18/25671-9 - Astronomical image processing and analysis using deep convolutional models
• Grantee: Ana Carolina Rodrigues Cavalcante Martinazzo
• Support Opportunities: Scholarships in Brazil - Master
• FAPESP's process: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery
• Grantee: Roberto Marcondes Cesar Junior
• Support Opportunities: Research Projects - Thematic Grants