Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorLopes, Leonardo Tadeu-
Autor(es): dc.creatorCarlos Guimaraes Pedronette, Daniel-
Data de aceite: dc.date.accessioned2025-08-21T15:36:48Z-
Data de disponibilização: dc.date.available2025-08-21T15:36:48Z-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2023-07-29-
Data de envio: dc.date.issued2022-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/WACV56688.2023.00559-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/246901-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/246901-
Descrição: dc.descriptionIn spite of the huge advances in supervised learning, the common requirement for extensive labeled datasets represents a severe bottleneck. In this scenario, other learning paradigms capable of addressing the challenge associated with the scarcity of labeled data represent a relevant alternative solution. This paper presents a novel clustering method called Self-Supervised Graph Convolutional Clustering (SGCC)1, which aims to exploit the strengths of different learning paradigms, combining unsupervised, semi-supervised, and self-supervised perspectives. An unsupervised manifold learning algorithm based on hypergraphs and ranking information is used to provide more effective and global similarity information. The hypergraph structures allow identifying representative items for each cluster, which are used to derive a set of small but high-confident clusters. Such clusters are taken as soft-labels for training a Graph Convolutional Network (GCN) in a semi-supervised classification task. Once trained in a self-supervised setting, the GCN is used to predict the cluster of remaining items. The proposed SGCC method was evaluated both in image and citation networks datasets and compared with classic and recent clustering methods, obtaining high-effective results in all scenarios.-
Descrição: dc.descriptionState University of São Paulo (UNESP)-
Descrição: dc.descriptionState University of São Paulo (UNESP)-
Formato: dc.format5623-5632-
Idioma: dc.languageen-
Relação: dc.relationProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectAlgorithms: Machine learning architectures-
Palavras-chave: dc.subjectand algorithms (including transfer)-
Palavras-chave: dc.subjectformulations-
Palavras-chave: dc.subjectImage recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)-
Título: dc.titleSelf-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.