• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. X3SEG: Model-Agnostic Explanations for the Semantic Segmentation of 3D Point Clouds with Prototypes and Criticism
 
  • Details
  • Full
Options
2021
  • Konferenzbeitrag

Titel

X3SEG: Model-Agnostic Explanations for the Semantic Segmentation of 3D Point Clouds with Prototypes and Criticism

Abstract
The proposed X3Seg approach generates model-agnostic, example-based explanations for the semantic segmentation of 3D point clouds. It retrieves the most similar 3D point sets (prototypes) as well as the most dissimilar point sets (criticism) to the spatially connected 3D point set which is to be explained. X3Seg comprises three methods for a holistic understanding of point-by-point class predictions: encompassing, selective, and predictive X3Seg. Prototypes and criticism are identified from a particularly generated prototype database by combining different similarity measures. To the best of our knowledge, X3Seg is the first model-agnostic explainable artificial intelligence (XAI) approach providing example-based explanations for the semantic segmentation of 3D data with prototypes and criticism. It is demonstrated on RangeNet53++[1] predictions for 3D point cloud data from the SemanticKITTI dataset.
Author(s)
Heide, Nina Felicitas
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Müller, Erik
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Petereit, Janko
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Heizmann, Michael
Hauptwerk
IEEE International Conference on Image Processing, ICIP 2021
Project(s)
ROBDEKON
Funder
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Konferenz
International Conference on Image Processing (ICIP) 2021
Thumbnail Image
DOI
10.1109/ICIP42928.2021.9506624
Language
Englisch
google-scholar
IOSB
Tags
  • explainable artificia...

  • Semantic Segmentation...

  • autonomous system

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022