• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Partner Events
    • EuroVisShort
    • EuroVisShort2021
    • View Item
    •   Eurographics DL Home
    • Eurographics Partner Events
    • EuroVisShort
    • EuroVisShort2021
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    VATUN: Visual Analytics for Testing and Understanding Convolutional Neural Networks

    Thumbnail
    View/Open
    007-011.pdf (5.293Mb)
    1043-file1.mp4 (11.95Mb)
    Date
    2021
    Author
    Park, Cheonbok ORCID
    Yang, Soyoung ORCID
    Na, Inyoup ORCID
    Chung, Sunghyo
    Shin, Sungbok ORCID
    Kwon, Bum Chul ORCID
    Park, Deokgun ORCID
    Choo, Jaegul ORCID
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    Convolutional neural networks (CNNs) are popularly used in a wide range of applications, such as computer vision, natural language processing, and human-computer interaction. However, testing and understanding a trained model is difficult and very time-consuming. This is because their inner mechanisms are often considered as a 'black-box' due to difficulty in understanding the causal relationships between processes and results. To help the testing and understanding of such models, we present a user-interactive visual analytics system, VATUN, to analyze a CNN-based image classification model. Users can accomplish the following four tasks in our integrated system: (1) detect data instances in which the model confuses classification, (2) compare outcomes of the model by manipulating the conditions of the image, (3) understand reasons for the prediction of the model by highlighting highly influential parts from the image, and (4) analyze the overall what-if scenarios when augmenting the instances for each class. Moreover, by combining multiple techniques, our system lets users analyze behavior of the model from various perspectives. We conduct a user study of an image classification scenario with three domain experts. Our study will contribute to reducing the time cost for testing and understanding the CNN-based models in several industrial areas.
    BibTeX
    @inproceedings {10.2312:evs.20211047,
    booktitle = {EuroVis 2021 - Short Papers},
    editor = {Agus, Marco and Garth, Christoph and Kerren, Andreas},
    title = {{VATUN: Visual Analytics for Testing and Understanding Convolutional Neural Networks}},
    author = {Park, Cheonbok and Yang, Soyoung and Na, Inyoup and Chung, Sunghyo and Shin, Sungbok and Kwon, Bum Chul and Park, Deokgun and Choo, Jaegul},
    year = {2021},
    publisher = {The Eurographics Association},
    ISBN = {978-3-03868-143-4},
    DOI = {10.2312/evs.20211047}
    }
    URI
    https://doi.org/10.2312/evs.20211047
    https://diglib.eg.org:443/handle/10.2312/evs20211047
    Collections
    • EuroVisShort2021

    Eurographics Association copyright © 2013 - 2023 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA
     

     

    Browse

    All of Eurographics DLCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2023 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA