| Campo DC | Valor | Lengua/Idioma |
|---|
| dc.contributor.author | Gomes, Jacó Cirino | - |
| dc.contributor.author | Borges, Lurdineide de Araújo Barbosa | - |
| dc.contributor.author | Borges, Díbio Leandro | - |
| dc.date.accessioned | 2025-09-19T10:18:18Z | - |
| dc.date.available | 2025-09-19T10:18:18Z | - |
| dc.date.issued | 2023-08-03 | - |
| dc.identifier.citation | GOMES, Jacó Cirino; BORGES, Lurdineide de Araújo Barbosa; BORGES, Díbio Leandro. A multi-layer feature fusion method for few-shot image classification. Sensors, Basel, v. 23, n. 15, 2023. DOI: https://doi.org/10.3390/s23156880. Disponível em: https://www.mdpi.com/1424-8220/23/15/6880. Acesso em: 03 jul. 2025. | pt_BR |
| dc.identifier.uri | http://repositorio.unb.br/handle/10482/52466 | - |
| dc.language.iso | eng | pt_BR |
| dc.publisher | MDPI | pt_BR |
| dc.rights | Acesso Aberto | pt_BR |
| dc.title | A multi-layer feature fusion method for few-shot image classification | pt_BR |
| dc.type | Artigo | pt_BR |
| dc.subject.keyword | Rede Neurais Convolucionais (CNNs) | pt_BR |
| dc.subject.keyword | Classificação de imagens | pt_BR |
| dc.subject.keyword | Multiescala | pt_BR |
| dc.subject.keyword | Aprendizagem métrica | pt_BR |
| dc.rights.license | (CC BY) © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). | pt_BR |
| dc.identifier.doi | https://doi.org/10.3390/s23156880 | pt_BR |
| dc.description.abstract1 | In image classification, few-shot learning deals with recognizing visual categories from a
few tagged examples. The degree of expressiveness of the encoded features in this scenario is a crucial
question that needs to be addressed in the models being trained. Recent approaches have achieved
encouraging results in improving few-shot models in deep learning, but designing a competitive
and simple architecture is challenging, especially considering its requirement in many practical
applications. This work proposes an improved few-shot model based on a multi-layer feature
fusion (FMLF) method. The presented approach includes extended feature extraction and fusion
mechanisms in the Convolutional Neural Network (CNN) backbone, as well as an effective metric to
compute the divergences in the end. In order to evaluate the proposed method, a challenging visual
classification problem, maize crop insect classification with specific pests and beneficial categories, is
addressed, serving both as a test of our model and as a means to propose a novel dataset. Experiments
were carried out to compare the results with ResNet50, VGG16, and MobileNetv2, used as feature
extraction backbones, and the FMLF method demonstrated higher accuracy with fewer parameters.
The proposed FMLF method improved accuracy scores by up to 3.62% in one-shot and 2.82% in fiveshot classification tasks compared to a traditional backbone, which uses only global image features. | pt_BR |
| dc.identifier.orcid | https://orcid.org/0000-0003-4810-5138 | pt_BR |
| dc.identifier.orcid | https://orcid.org/0000-0001-9284-3299 | pt_BR |
| dc.identifier.orcid | https://orcid.org/0000-0002-4868-0629 | pt_BR |
| dc.contributor.affiliation | University of Brasília, Department of Mechanical Engineering | pt_BR |
| dc.contributor.affiliation | Embrapa Cerrados | pt_BR |
| dc.contributor.affiliation | University of Brasília, Department of Computer Science | pt_BR |
| dc.description.unidade | Instituto de Ciências Exatas (IE) | pt_BR |
| dc.description.unidade | Departamento de Ciência da Computação (IE CIC) | pt_BR |
| dc.description.ppg | Programa de Pós-Graduação em Sistemas Mecatrônicos | pt_BR |
| Aparece en las colecciones: | Artigos publicados em periódicos e afins
|
