Repository logo
 
Publication

Fine-grained fish classification from small to large datasets with vision transformers

2024Journal article Open access
Simple item page
dc.contributor.authorVeiga, Ricardo
dc.contributor.authorRodrigues, Joao
dc.date.accessioned2024-11-02T13:23:58Z
dc.date.available2024-11-02T13:23:58Z
dc.date.issued2024
dc.description.abstractFish species Fine-Grained Visual Classification (FGVC) is important for ecological research, environmental management, and biodiversity monitoring, as accurate fish species identification is crucial for assessing the health of marine ecosystems, monitoring changes in biodiversity, and converting conservation plans into action. Although Convolutional Neural Network (CNN)s have been the conventional approach for FGVC, their effectiveness in differentiating visually similar species is not always satisfactory. The advent of Vision Transformer (ViT)s, in particular the Shifted window (Swin) Transformer, has demonstrated potential in addressing these issues by using sophisticated self-attention and feature extraction techniques. This paper proposes a method of combining the FGVC Plug-in Module (FGVC-PIM) and the Swin Transformer. The FGVC-PIM improves classification by concentrating on the most discriminative image regions, while the Swin Transformer acts as the framework and provides strong hierarchical feature extraction. The performance of the method was assessed on 14 different datasets, which included 19 distinct subsets with varying environmental conditions and image quality. With the proposed method it was achieved state-of-the-art results in 13 of these subsets, exhibiting better accuracy and robustness than previous methods, in 2 subsets (not yet explored by other authors) new baseline results are presented, and in the remaining 4 it was achieved results always above 83%.eng
dc.description.sponsorshipUIDP/04516/2020; 2022.11602.BD
dc.identifier.doi10.1109/access.2024.3443654
dc.identifier.issn2169-3536
dc.identifier.urihttp://hdl.handle.net/10400.1/26198
dc.language.isoeng
dc.peerreviewedyes
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relationNOVA Laboratory for Computer Science and Informatics
dc.relation.ispartofIEEE Access
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectTransformers
dc.subjectComputer vision
dc.subjectFeature extraction
dc.subjectTask analysis
dc.subjectConvolutional neural networks
dc.subjectBiological system modeling
dc.subjectBiodiversity
dc.subjectMarine ecosystems
dc.subjectMonitoring
dc.subjectFish
dc.subjectFine-grained visual classification
dc.subjectMarine biodiversity monitoring
dc.subjectSwin transformer
dc.titleFine-grained fish classification from small to large datasets with vision transformerseng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleNOVA Laboratory for Computer Science and Informatics
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04516%2F2020/PT
oaire.citation.endPage113660
oaire.citation.startPage113642
oaire.citation.titleIEEE Access
oaire.citation.volume12
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameVeiga
person.familyNameRodrigues
person.givenNameRicardo
person.givenNameJoao
person.identifier1603578
person.identifier.ciencia-idD212-85A6-C85A
person.identifier.ciencia-id8A19-98F7-9914
person.identifier.orcid0000-0002-7557-8304
person.identifier.orcid0000-0002-3562-6025
person.identifier.scopus-author-id57203130604
person.identifier.scopus-author-id55807461600
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication60cb9fb6-94b2-4657-935e-3e7eea696a49
relation.isAuthorOfPublication683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isAuthorOfPublication.latestForDiscovery60cb9fb6-94b2-4657-935e-3e7eea696a49
relation.isProjectOfPublication1122b3d4-9740-4ad7-9abf-86bb7a3615da
relation.isProjectOfPublication.latestForDiscovery1122b3d4-9740-4ad7-9abf-86bb7a3615da

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fine-Grained_Fish_Classification_From_Small_to_Large_Datasets_With_Vision_Transformers.pdf
Size:
3.97 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.46 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)