Fine-Grained Generalized Zero-Shot Learning
Date
2022-01-02
Student ID
Research Supervisor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Fine-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.
Description
Keywords
TECHNOLOGY::Electrical engineering, electronics and photonics::Electrical engineering
Citation
Department Name
Publisher
North South University