skip to main content
Idioma:

A self-supervised learning approach for astronomical images

Martinazzo, Ana Carolina Rodrigues Cavalcante

Biblioteca Digital de Teses e Dissertações da USP; Universidade de São Paulo; Instituto de Matemática e Estatística 2021-10-25

Acesso online. A biblioteca também possui exemplares impressos.

  • Título:
    A self-supervised learning approach for astronomical images
  • Autor: Martinazzo, Ana Carolina Rodrigues Cavalcante
  • Orientador: Hirata, Nina Sumiko Tomita
  • Assuntos: Aprendizagem Auto-Supervisionada; Processamento De Imagens Astronômicas; Redes Neurais Convolucionais; Astronomical Image Processing; Convolutional Neural Networks; Self-Supervised Learning
  • Notas: Dissertação (Mestrado)
  • Descrição: Modern astronomical sky surveys are providing us with a flood of images with unusual characteristics, such as numerous channels, saturated signals, faint signals, uncertainties, and varying signal-to-noise ratios. The complexity and diversity of these images make them an adequate use case for deep convolutional neural networks. Moreover, they yield millions of detected objects whose classes are mostly unknown. Given this context, the main objective of this work is to investigate deep representation learning approaches for multichannel astronomical images, focusing on finding reasonable representations that do not require labeled data and that make use of some domain knowledge. A reasonable representation may be thought of as one that contains enough discriminative information, that can be later used for higher-level tasks such as object classification, outlier detection and clustering. We propose a self-supervised learning approach that makes use of astronomical properties (more specifically, magnitudes) of the objects in order to pretrain deep neural networks with unlabeled data. We choose the task of classifying galaxies, stars and quasars as a baseline for quantifying the quality of the learned representations, and empirically demonstrate that our approach yields results that are better than -- or at least comparable to -- a benchmark RGB model pretrained on ImageNet.
  • DOI: 10.11606/D.45.2021.tde-11012022-203357
  • Editor: Biblioteca Digital de Teses e Dissertações da USP; Universidade de São Paulo; Instituto de Matemática e Estatística
  • Data de criação/publicação: 2021-10-25
  • Formato: Adobe PDF
  • Idioma: Inglês
Links
Voltar para lista de resultados
Ir para página anteriorAnterior Resultado  13 AvançarIr para próxima página

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.