Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications

Simple item page
dc.contributor.authorJanik, Adriannaen_US
dc.contributor.authorSankaran, Krisen_US
dc.contributor.authorOrtiz, Anthonyen_US
dc.contributor.editorArchambault, Daniel and Nabney, Ian and Peltonen, Jaakkoen_US
dc.date.accessioned2019-06-02T18:23:43Z
dc.date.available2019-06-02T18:23:43Z
dc.date.issued2019
dc.description.abstractIn 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.en_US
dc.description.sectionheadersPapers
dc.description.seriesinformationMachine Learning Methods in Visualisation for Big Data
dc.identifier.doi10.2312/mlvis.20191158
dc.identifier.isbn978-3-03868-089-5
dc.identifier.pages7-11
dc.identifier.urihttps://doi.org/10.2312/mlvis.20191158
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/mlvis20191158
dc.publisherThe Eurographics Associationen_US
dc.subjectHuman
dc.subjectcentered computing
dc.subjectInformation visualization
dc.subjectComputing methodologies
dc.subjectKnowledge representation and reasoning
dc.subjectImage segmentation"
dc.titleInterpreting Black-Box Semantic Segmentation Models in Remote Sensing Applicationsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
007-011.pdf
Size:
2.2 MB
Format:
Adobe Portable Document Format
Download
Collections
Machine Learning Methods in Visualisation for Big Data 2019