• Login
    View Item 
    •   Eurographics DL Home
    • Eurographics Partner Events
    • Machine Learning Methods in Visualisation for Big Data
    • Machine Learning Methods in Visualisation for Big Data 2019
    • View Item
    •   Eurographics DL Home
    • Eurographics Partner Events
    • Machine Learning Methods in Visualisation for Big Data
    • Machine Learning Methods in Visualisation for Big Data 2019
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications

    Thumbnail
    View/Open
    007-011.pdf (2.202Mb)
    Date
    2019
    Author
    Janik, Adrianna
    Sankaran, Kris
    Ortiz, Anthony
    Pay-Per-View via TIB Hannover:

    Try if this item/paper is available.

    Metadata
    Show full item record
    Abstract
    In the interpretability literature, attention is focused on understanding black-box classifiers, but many problems ranging from medicine through agriculture and crisis response in humanitarian aid are tackled by semantic segmentation models. The absence of interpretability for these canonical problems in computer vision motivates this study. In this study we present a usercentric approach that blends techniques from interpretability, representation learning, and interactive visualization. It allows to visualize and link latent representation to real data instances as well as qualitatively assess strength of predictions. We have applied our method to a deep learning model for semantic segmentation, U-Net, in a remote sensing application of building detection. This application is of high interest for humanitarian crisis response teams that rely on satellite images analysis. Preliminary results shows utility in understanding semantic segmentation models, demo presenting the idea is available online.
    BibTeX
    @inproceedings {10.2312:mlvis.20191158,
    booktitle = {Machine Learning Methods in Visualisation for Big Data},
    editor = {Archambault, Daniel and Nabney, Ian and Peltonen, Jaakko},
    title = {{Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications}},
    author = {Janik, Adrianna and Sankaran, Kris and Ortiz, Anthony},
    year = {2019},
    publisher = {The Eurographics Association},
    ISBN = {978-3-03868-089-5},
    DOI = {10.2312/mlvis.20191158}
    }
    URI
    https://doi.org/10.2312/mlvis.20191158
    https://diglib.eg.org:443/handle/10.2312/mlvis20191158
    Collections
    • Machine Learning Methods in Visualisation for Big Data 2019

    Eurographics Association copyright © 2013 - 2022 
    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

    BibTeX | TOC

    Create BibTeX Create Table of Contents

    Eurographics Association copyright © 2013 - 2022 
    Send Feedback | Contact - Imprint | Data Privacy Policy | Disable Google Analytics
    Theme by @mire NV
    System hosted at  Graz University of Technology.
    TUGFhA