Cargando…

Feature fusion network based on few-shot fine-grained classification

The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where t...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Yajie, Feng, Yuxuan, Zhu, Li, Fu, Haitao, Pan, Xin, Jin, Chenlei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10665847/
https://www.ncbi.nlm.nih.gov/pubmed/38023453
http://dx.doi.org/10.3389/fnbot.2023.1301192
_version_ 1785138916702027776
author Yang, Yajie
Feng, Yuxuan
Zhu, Li
Fu, Haitao
Pan, Xin
Jin, Chenlei
author_facet Yang, Yajie
Feng, Yuxuan
Zhu, Li
Fu, Haitao
Pan, Xin
Jin, Chenlei
author_sort Yang, Yajie
collection PubMed
description The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets.
format Online
Article
Text
id pubmed-10665847
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-106658472023-01-01 Feature fusion network based on few-shot fine-grained classification Yang, Yajie Feng, Yuxuan Zhu, Li Fu, Haitao Pan, Xin Jin, Chenlei Front Neurorobot Neuroscience The objective of few-shot fine-grained learning is to identify subclasses within a primary class using a limited number of labeled samples. However, many current methodologies rely on the metric of singular feature, which is either global or local. In fine-grained image classification tasks, where the inter-class distance is small and the intra-class distance is big, relying on a singular similarity measurement can lead to the omission of either inter-class or intra-class information. We delve into inter-class information through global measures and tap into intra-class information via local measures. In this study, we introduce the Feature Fusion Similarity Network (FFSNet). This model employs global measures to accentuate the differences between classes, while utilizing local measures to consolidate intra-class data. Such an approach enables the model to learn features characterized by enlarge inter-class distances and reduce intra-class distances, even with a limited dataset of fine-grained images. Consequently, this greatly enhances the model's generalization capabilities. Our experimental results demonstrated that the proposed paradigm stands its ground against state-of-the-art models across multiple established fine-grained image benchmark datasets. Frontiers Media S.A. 2023-11-09 /pmc/articles/PMC10665847/ /pubmed/38023453 http://dx.doi.org/10.3389/fnbot.2023.1301192 Text en Copyright © 2023 Yang, Feng, Zhu, Fu, Pan and Jin. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Yang, Yajie
Feng, Yuxuan
Zhu, Li
Fu, Haitao
Pan, Xin
Jin, Chenlei
Feature fusion network based on few-shot fine-grained classification
title Feature fusion network based on few-shot fine-grained classification
title_full Feature fusion network based on few-shot fine-grained classification
title_fullStr Feature fusion network based on few-shot fine-grained classification
title_full_unstemmed Feature fusion network based on few-shot fine-grained classification
title_short Feature fusion network based on few-shot fine-grained classification
title_sort feature fusion network based on few-shot fine-grained classification
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10665847/
https://www.ncbi.nlm.nih.gov/pubmed/38023453
http://dx.doi.org/10.3389/fnbot.2023.1301192
work_keys_str_mv AT yangyajie featurefusionnetworkbasedonfewshotfinegrainedclassification
AT fengyuxuan featurefusionnetworkbasedonfewshotfinegrainedclassification
AT zhuli featurefusionnetworkbasedonfewshotfinegrainedclassification
AT fuhaitao featurefusionnetworkbasedonfewshotfinegrainedclassification
AT panxin featurefusionnetworkbasedonfewshotfinegrainedclassification
AT jinchenlei featurefusionnetworkbasedonfewshotfinegrainedclassification