A Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognition

Simple item page
dc.contributor.authorHimabindu, Dakshayani D
dc.contributor.authorKumar, Praveen S
dc.coverage.issue2cs
dc.coverage.volume27cs
dc.date.accessioned2022-01-26T08:21:49Z
dc.date.available2022-01-26T08:21:49Z
dc.date.issued2021-12-21cs
dc.description.abstractIn the recent advancements attention mechanism in deep learning had played a vital role in proving better results in tasks under computer vision. There exists multiple kinds of works under attention mechanism which includes under image classification, fine-grained visual recognition, image captioning, video captioning, object detection and recognition tasks. Global and local attention are the two attention based mechanisms which helps in interpreting the attentive partial. Considering this criteria, there exists channel and spatial attention where in channel attention considers the most attentive channel among the produced block of channels and spatial attention considers which region among the space needs to be focused on. We have proposed a streamlined attention block module which helps in enhancing the feature based learning with less number of additional layers i.e., a GAP layer followed by a linear layer with an incorporation of second order pooling(GSoP) after every layer in the utilized encoder. This mechanism has produced better range dependencies by the conducted experimentation. We have experimented our model on CIFAR-10, CIFAR-100 and FGVC-Aircrafts datasets considering finegrained visual recognition. We were successful in achieving state-of-the-result for FGVC-Aircrafts with an accuracy of 97%.en
dc.formattextcs
dc.format.extent59-67cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationMendel. 2021 vol. 27, č. 2, s. 59-67. ISSN 1803-3814cs
dc.identifier.doi10.13164/mendel.2021.2.059en
dc.identifier.issn2571-3701
dc.identifier.issn1803-3814
dc.identifier.urihttp://hdl.handle.net/11012/203393
dc.language.isoencs
dc.publisherInstitute of Automation and Computer Science, Brno University of Technologycs
dc.relation.ispartofMendelcs
dc.relation.urihttps://mendel-journal.org/index.php/mendel/article/view/159cs
dc.rightsCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0en
dc.subjectVisual attentionen
dc.subjectspatial attentionen
dc.subjectchannel attentionen
dc.subjectfine-grained visual recognitionen
dc.subjectimage classificationen
dc.subjectdeep learningen
dc.titleA Streamlined Attention Mechanism for Image Classification and Fine-Grained Visual Recognitionen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta strojního inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
159-Article Text-356-3-10-20220124.pdf
Size:
564.37 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Vol. 27, No. 2