Fine-Grained Generalized Zero-Shot Learning

Simple item page
creativework.keywordsZero-shot object recognition
dc.contributor.advisorDr. Shafin Rahman
dc.contributor.authorSumaia Rahman Twinkle
dc.contributor.authorMohibul hasan Tarek
dc.contributor.authorAnondo Hossain Rafi
dc.contributor.authorMahmudur Rahman Ifat
dc.contributor.editor
dc.contributor.id1430058042
dc.contributor.id1813218042
dc.contributor.id1813264042
dc.contributor.id1912175642
dc.date.accessioned2024-03-24
dc.date.accessioned2024-03-24T07:49:21Z
dc.date.available2024-03-24T07:49:21Z
dc.date.issued2022-01-02
dc.description.abstractFine-Grained Generalized Zero-Shot learning is the state of the art technology in the domain of computer vision and pattern recognition. In this project we are prepare our model to do GZSL where during the testing time an unseen/novel image will put as an in put to the model which image classes aren’t using during the training time. To overcomethisChallengeweleveragethesemanticinformationofthebothseen(source) and unseen(Target)classes to bridge the gap within them. To solve the fine-grained GZSL recognition of visually similar classes. To find out the difference between small intra-class and large intra-class variation, we use the dense attribute attention mechanism where for each attribute focus es on the most relevant image regions, obtaining attributes features. For classification training, we compute the score so attributes vector and classify the image attributes whose similarities is maximum with these mantic vector class. We conduct the experiment on the two popular data sets of CUB and AWA2 to examine our model.
dc.description.degreeUndergraduate
dc.identifier.cd600000019
dc.identifier.print-thesisTo be assigned
dc.identifier.urihttps://repository.northsouth.edu/handle/123456789/475
dc.language.isoen_US
dc.publisherNorth South University
dc.rights© NSU Library
dc.subjectTECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering
dc.titleFine-Grained Generalized Zero-Shot Learning
oaire.citation.endPage44
oaire.citation.startPage1
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
600000019.pdf
Size:
2.56 MB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
600000019-abstract.pdf
Size:
600.32 KB
Format:
Adobe Portable Document Format
Description:
Download
Thumbnail Image
Name:
600000019.pdf
Size:
2.56 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.93 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Theses - Undergraduate