• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Effect of superpixel aggregation on explanations in LIME - A case study with biological data
 
  • Details
  • Full
Options
2020
Conference Paper
Title

Effect of superpixel aggregation on explanations in LIME - A case study with biological data

Abstract
End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into superpixels based on the Quick-Shift algorithm. In this paper, we present an explorative study of how different superpixel methods, namely Felzenszwalb, SLIC and Compact-Watershed, impact the generated visual explanations. We compare the resulting relevance areas with the image parts marked by a human reference. Results show that image parts selected as relevant strongly vary depending on the applied method. Quick-Shift resulted in the least and Compact-Watershed in the highest correspondence with the reference relevance areas.
Author(s)
Schallner, L.
Rabold, J.
Scholz, O.
Schmid, U.
Mainwork
Machine Learning and Knowledge Discovery in Databases. Proceedings. Pt.I  
Conference
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2019  
Open Access
DOI
10.1007/978-3-030-43823-4_13
Additional full text version
Landing Page
Language
English
Fraunhofer-Institut für Integrierte Schaltungen IIS  
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024