Cargando…

Few-shot image classification algorithm based on attention mechanism and weight fusion

Aiming at the existing problems of metric-based methods, there are problems such as inadequate feature extraction, inaccurate class feature representation, and single similarity measurement. A new model based on attention mechanism and weight fusion strategy is proposed in this paper. Firstly, the i...

Descripción completa

Detalles Bibliográficos
Autores principales: Meng, Xiaoxia, Wang, Xiaowei, Yin, Shoulin, Li, Hang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Berlin Heidelberg 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9977640/
http://dx.doi.org/10.1186/s44147-023-00186-9
_version_ 1784899338631118848
author Meng, Xiaoxia
Wang, Xiaowei
Yin, Shoulin
Li, Hang
author_facet Meng, Xiaoxia
Wang, Xiaowei
Yin, Shoulin
Li, Hang
author_sort Meng, Xiaoxia
collection PubMed
description Aiming at the existing problems of metric-based methods, there are problems such as inadequate feature extraction, inaccurate class feature representation, and single similarity measurement. A new model based on attention mechanism and weight fusion strategy is proposed in this paper. Firstly, the image is passed through the conv4 network with channel attention mechanism and space attention mechanism to obtain the feature map of the image. On this basis, the fusion strategy is used to extract class-level feature representations according to the difference in contributions of different samples to class-level feature representations. Finally, the similarity scores of query set samples are calculated through the network to predict the classification. Experimental results on the miniImageNet dataset and the omniglot dataset demonstrate the effectiveness of the proposed method.
format Online
Article
Text
id pubmed-9977640
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Springer Berlin Heidelberg
record_format MEDLINE/PubMed
spelling pubmed-99776402023-03-02 Few-shot image classification algorithm based on attention mechanism and weight fusion Meng, Xiaoxia Wang, Xiaowei Yin, Shoulin Li, Hang J. Eng. Appl. Sci. Research Aiming at the existing problems of metric-based methods, there are problems such as inadequate feature extraction, inaccurate class feature representation, and single similarity measurement. A new model based on attention mechanism and weight fusion strategy is proposed in this paper. Firstly, the image is passed through the conv4 network with channel attention mechanism and space attention mechanism to obtain the feature map of the image. On this basis, the fusion strategy is used to extract class-level feature representations according to the difference in contributions of different samples to class-level feature representations. Finally, the similarity scores of query set samples are calculated through the network to predict the classification. Experimental results on the miniImageNet dataset and the omniglot dataset demonstrate the effectiveness of the proposed method. Springer Berlin Heidelberg 2023-03-02 2023 /pmc/articles/PMC9977640/ http://dx.doi.org/10.1186/s44147-023-00186-9 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/ (https://creativecommons.org/publicdomain/zero/1.0/) ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
spellingShingle Research
Meng, Xiaoxia
Wang, Xiaowei
Yin, Shoulin
Li, Hang
Few-shot image classification algorithm based on attention mechanism and weight fusion
title Few-shot image classification algorithm based on attention mechanism and weight fusion
title_full Few-shot image classification algorithm based on attention mechanism and weight fusion
title_fullStr Few-shot image classification algorithm based on attention mechanism and weight fusion
title_full_unstemmed Few-shot image classification algorithm based on attention mechanism and weight fusion
title_short Few-shot image classification algorithm based on attention mechanism and weight fusion
title_sort few-shot image classification algorithm based on attention mechanism and weight fusion
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9977640/
http://dx.doi.org/10.1186/s44147-023-00186-9
work_keys_str_mv AT mengxiaoxia fewshotimageclassificationalgorithmbasedonattentionmechanismandweightfusion
AT wangxiaowei fewshotimageclassificationalgorithmbasedonattentionmechanismandweightfusion
AT yinshoulin fewshotimageclassificationalgorithmbasedonattentionmechanismandweightfusion
AT lihang fewshotimageclassificationalgorithmbasedonattentionmechanismandweightfusion