Show simple item record

dc.contributor.advisorKhriyenko, Oleksiy
dc.contributor.authorZhang, Yindong
dc.date.accessioned2020-06-04T11:50:23Z
dc.date.available2020-06-04T11:50:23Z
dc.date.issued2020
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/69720
dc.description.abstractZero-shot learning (ZSL) is widely studied in recent years to solve the problem of lacking annotations. Currently, most studies on ZSL are for image classification and object detection. But zero-shot semantic segmentation, pixel level classification, is still at its early stage. Therefore, this thesis proposes to extend a zero-shot image classification model, Relation Network (RN), to semantic segmentation tasks. This thesis modifies the structure of RN based on other state-of-the-arts semantic segmentation models (i.e. U-Net and DeepLab) and utilizes word embeddings from Caltech-UCSD Birds 200-2011 attributes and natural language processing models (i.e. word2vec and fastText). Because meta-learning is limited to binary tasks, this thesis proposes to join multiple binary semantic segmentation pipelines for multi-class semantic segmentation. It is proved by experiments that RN could improve accuracy of U-Net with the help of semantic side information on binary semantic segmentation and it could also be applied on multi-class semantic segmentation with simpler structure than the baseline model, SPNet, but higher accuracy under ZSL setting. However, the capability of RN under generalized zero-shot learning (GZSL) setting still needs improvement. This thesis also studies on how different word embeddings, network structures and data affect RN and what could be done to improve its results.en
dc.format.extent73
dc.language.isoen
dc.subject.otherzero-shot learning
dc.subject.othersemantic segmentation
dc.subject.otherrelation network
dc.subject.othermeta-learning
dc.titleZero-shot semantic segmentation using relation network
dc.identifier.urnURN:NBN:fi:jyu-202006043976
dc.type.ontasotMaster’s thesisen
dc.type.ontasotPro gradu -tutkielmafi
dc.contributor.tiedekuntaInformaatioteknologian tiedekuntafi
dc.contributor.tiedekuntaFaculty of Information Technologyen
dc.contributor.laitosInformaatioteknologiafi
dc.contributor.laitosInformation Technologyen
dc.contributor.yliopistoJyväskylän yliopistofi
dc.contributor.yliopistoUniversity of Jyväskyläen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineMathematical Information Technologyen
dc.rights.copyrightJulkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.fi
dc.rights.copyrightThis publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.en
dc.contributor.oppiainekoodi602
dc.subject.ysosegmentointi
dc.subject.ysokoneoppiminen
dc.subject.ysosegmentation
dc.subject.ysomachine learning


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record