University of Jyväskylä | JYX Digital Repository

  • English  | Give feedback |
    • suomi
    • English
 
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  • JYX
  • Opinnäytteet
  • Pro gradu -tutkielmat
  • View Item
JYX > Opinnäytteet > Pro gradu -tutkielmat > View Item

Zero-shot semantic segmentation using relation network

Thumbnail
View/Open
2.0Mb

Downloads:  
Show download detailsHide download details  
Authors
Zhang, Yindong
Date
2020
Discipline
TietotekniikkaMathematical Information Technology
Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.

 
Zero-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. ...
Keywords
zero-shot learning semantic segmentation relation network meta-learning segmentointi koneoppiminen segmentation machine learning
URI

http://urn.fi/URN:NBN:fi:jyu-202006043976

Metadata
Show full item record
Collections
  • Pro gradu -tutkielmat [23442]

Related items

Showing items with similar title or keywords.

  • Editorial for the special issue "Frontiers in spectral imaging and 3D technologies for geospatial solutions" 

    Honkavaara, Eija; Karantzalos, Konstantinos; Liang, Xinlian; Nocerino, Erica; Pölönen, Ilkka; Rönnholm, Petri (MDPI, 2019)
    This Special Issue hosts papers on the integrated use of spectral imaging and 3D technologies in remote sensing, including novel sensors, evolving machine learning technologies for data analysis, and the utilization of ...
  • Zero-shot Semantic Segmentation using Relation Network 

    Zhang, Yindong; Khriyenko, Oleksiy (FRUCT Oy, 2021)
    Zero-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, ...
  • Emotions and Activity Recognition System Using Wearable Device Sensors 

    Rumiantcev, Mikhail (FRUCT Oy, 2021)
    Nowadays machines have become extremely smart, there are a lot of existing services that seemed to be unexpectable and futuristic decades or even a few years ago. However, artificial intelligence is still far from human ...
  • Deep semantic segmentation for skin cancer detection from hyperspectral images 

    Karhu, Anette (2020)
    As skin cancer types are a growing concern worldwide, a new screening tool combined with automation may help the clinicians in clinical examinations of lesions. A novel hyperspectral imager prototype has been noted to be ...
  • Multilabel segmentation of cancer cell culture on vascular structures with deep neural networks 

    Rahkonen, Samuli; Koskinen, Emilia; Pölönen, Ilkka; Heinonen, Tuula; Ylikomi, Timo; Äyrämö, Sami; Eskelinen, Matti A. (SPIE, 2020)
    New increasingly complex in vitro cancer cell models are being developed. These new models seem to represent the cell behavior in vivo more accurately and have better physiological relevance than prior models. An efficient ...
  • Browse materials
  • Browse materials
  • Articles
  • Conferences and seminars
  • Electronic books
  • Historical maps
  • Journals
  • Tunes and musical notes
  • Photographs
  • Presentations and posters
  • Publication series
  • Research reports
  • Research data
  • Study materials
  • Theses

Browse

All of JYXCollection listBy Issue DateAuthorsSubjectsPublished inDepartmentDiscipline

My Account

Login

Statistics

View Usage Statistics
  • How to publish in JYX?
  • Self-archiving
  • Publish Your Thesis Online
  • Publishing Your Dissertation
  • Publication services

Open Science at the JYU
 
Data Protection Description

Accessibility Statement

Unless otherwise specified, publicly available JYX metadata (excluding abstracts) may be freely reused under the CC0 waiver.
Open Science Centre