Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/WACV56688.2023.00559 http://hdl.handle.net/11449/246901 |
Resumo: | In 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. |
id |
UNSP_a2abddb1b0cb82fdde872a1ea6e9ca76 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/246901 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional NetworksAlgorithms: Machine learning architecturesand algorithms (including transfer)formulationsImage recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)In 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.State University of São Paulo (UNESP)State University of São Paulo (UNESP)Universidade Estadual Paulista (UNESP)Lopes, Leonardo Tadeu [UNESP]Carlos Guimaraes Pedronette, Daniel [UNESP]2023-07-29T12:53:40Z2023-07-29T12:53:40Z2023-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject5623-5632http://dx.doi.org/10.1109/WACV56688.2023.00559Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023, p. 5623-5632.http://hdl.handle.net/11449/24690110.1109/WACV56688.2023.005592-s2.0-85148999634Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023info:eu-repo/semantics/openAccess2023-07-29T12:53:40Zoai:repositorio.unesp.br:11449/246901Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T14:11:17.974637Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
title |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
spellingShingle |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks Lopes, Leonardo Tadeu [UNESP] Algorithms: Machine learning architectures and algorithms (including transfer) formulations Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning) |
title_short |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
title_full |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
title_fullStr |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
title_full_unstemmed |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
title_sort |
Self-Supervised Clustering based on Manifold Learning and Graph Convolutional Networks |
author |
Lopes, Leonardo Tadeu [UNESP] |
author_facet |
Lopes, Leonardo Tadeu [UNESP] Carlos Guimaraes Pedronette, Daniel [UNESP] |
author_role |
author |
author2 |
Carlos Guimaraes Pedronette, Daniel [UNESP] |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Lopes, Leonardo Tadeu [UNESP] Carlos Guimaraes Pedronette, Daniel [UNESP] |
dc.subject.por.fl_str_mv |
Algorithms: Machine learning architectures and algorithms (including transfer) formulations Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning) |
topic |
Algorithms: Machine learning architectures and algorithms (including transfer) formulations Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning) |
description |
In 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. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T12:53:40Z 2023-07-29T12:53:40Z 2023-01-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/WACV56688.2023.00559 Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023, p. 5623-5632. http://hdl.handle.net/11449/246901 10.1109/WACV56688.2023.00559 2-s2.0-85148999634 |
url |
http://dx.doi.org/10.1109/WACV56688.2023.00559 http://hdl.handle.net/11449/246901 |
identifier_str_mv |
Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023, p. 5623-5632. 10.1109/WACV56688.2023.00559 2-s2.0-85148999634 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
5623-5632 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128329033711616 |