Feature Fusion and Augmentation based on Manifold Ranking for Image Classification

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorPereira-Ferrero, Vanessa Helena-
Autor(es): dc.creatorValem, Lucas Pascotti-
Autor(es): dc.creatorLeticio, Gustavo Rosseto-
Autor(es): dc.creatorPedronette, Daniel Carlos Guimarães-
Data de aceite: dc.date.accessioned2025-08-21T22:23:57Z-
Data de disponibilização: dc.date.available2025-08-21T22:23:57Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2022-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/AIKE59827.2023.00020-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/307868-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/307868-
Descrição: dc.descriptionDespite the great advances in the field of image classification, the association of ideal approaches that can bring improved results, considering different datasets, is still an open challenge. In this work, a novel approach is presented, based on a combination of compared strategies: features extraction for early fusion; rankings based on manifold learning for late fusion; and feature augmentation applied in a long short-term memory (LSTM) algorithm. The proposed method aims to investigate the effect of feature fusion (early fusion) and rankings fusion (late fusion) in the final results of image classification. The experimental results showed that the proposed strategies improved the accuracy of results in different tested datasets (such as CIFAR10, Stanford Dogs, Linnaeus5, Flowers102, and Flowers17) using a fusion of features from three convolutional neural networks - CNNs (ResNet152, VGG16, DPN92) and its respective generated rankings. The results indicated significant improvements and showed the potential of the approach proposed for image classification.-
Descrição: dc.descriptionMicrosoft Research-
Descrição: dc.descriptionPetrobras-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing (DEMAC) São Paulo State University (UNESP), São Paulo-
Descrição: dc.descriptionDepartment of Statistics Applied Mathematics and Computing (DEMAC) São Paulo State University (UNESP), São Paulo-
Descrição: dc.descriptionPetrobras: 2023/00095-3-
Formato: dc.format75-82-
Idioma: dc.languageen-
Relação: dc.relationProceedings - 2023 IEEE 6th International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectearly fusion-
Palavras-chave: dc.subjectfeature fusion-
Palavras-chave: dc.subjectimage classification-
Palavras-chave: dc.subjectlate fusion-
Palavras-chave: dc.subjectLSTM-
Palavras-chave: dc.subjectmanifold learning-
Palavras-chave: dc.subjectranking-
Título: dc.titleFeature Fusion and Augmentation based on Manifold Ranking for Image Classification-
Tipo de arquivo: dc.typeaula digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.