| Texto completo | |
| Autor(es): |
A M Oliveira, Artur Andre
;
Espadoto, Mateus
;
Hirata, Roberto, Jr.
;
T Hirata, Nina S.
;
Telea, Alexandru C.
Número total de Autores: 5
|
| Tipo de documento: | Artigo Científico |
| Fonte: | COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VISIGRAPP 2021; v. 1691, p. 27-pg., 2023-01-01. |
| Resumo | |
Dimensionality reduction (DR) is an essential tool for the visualization of high-dimensional data. The recently proposed Self-Supervised Network Projection (SSNP) method addresses DR with a number of attractive features, such as high computational scalability, genericity, stability and out-of-sample support, computation of an inverse mapping, and the ability of data clustering. Yet, SSNP has an involved computational pipeline using self-supervision based on labels produced by clustering methods and two separate deep learning networks with multiple hyperparameters. In this paper we explore the SSNP method in detail by studying its hyperparameter space and pseudo-labeling strategies. We show how these affect SSNP's quality and how to set them to optimal values based on extensive evaluations involving multiple datasets, DR methods, and clustering algorithms. (AU) | |
| Processo FAPESP: | 17/25835-9 - Interpretação de imagens e de modelos de aprendizado profundos |
| Beneficiário: | Nina Sumiko Tomita Hirata |
| Modalidade de apoio: | Auxílio à Pesquisa - Parceria para Inovação Tecnológica - PITE |
| Processo FAPESP: | 15/22308-2 - Representações intermediárias em Ciência Computacional para descoberta de conhecimento |
| Beneficiário: | Roberto Marcondes Cesar Junior |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |
| Processo FAPESP: | 20/13275-1 - Administrador da cyberinfraestrutura do projeto |
| Beneficiário: | Mateus Espadoto |
| Modalidade de apoio: | Bolsas no Brasil - Programa Capacitação - Treinamento Técnico |