• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. ScrutinAI: A Visual Analytics Approach for the Semantic Analysis of Deep Neural Network Predictions
 
  • Details
  • Full
Options
02 June 2022
Conference Paper
Titel

ScrutinAI: A Visual Analytics Approach for the Semantic Analysis of Deep Neural Network Predictions

Abstract
We present ScrutinAI, a Visual Analytics approach to exploit semantic understanding for deep neural network (DNN) predictions analysis, focusing on models for object detection and semantic segmentation. Typical fields of application for such models, e.g. autonomous driving or healthcare, have a high demand for detecting and mitigating data- and model-inherent shortcomings. Our approach aims to help analysts use their semantic understanding to identify and investigate potential weaknesses in DNN models. ScrutinAI therefore includes interactive visualizations of the model's inputs and outputs, interactive plots with linked brushing, and data filtering with textual queries on descriptive meta data. The tool fosters hypothesis driven knowledge generation which aids in understanding the model's inner reasoning. Insights gained during the analysis process mitigate the "black-box character" of the DNN and thus support model improvement and generation of a safety argumentation for AI applications. We present a case study on the investigation of DNN models for pedestrian detection from the automotive domain.
Author(s)
Haedecke, Elena Gina
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Mock, Michael
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Akila, Maram
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Hauptwerk
EuroVA 2022, 13th International EuroVis Workshop on Visual Analytics
Project(s)
KI Absicherung
ZERTIFIZIERTE KI
Funder
Bundesministerium für Wirtschaft und Klimaschutz -BMWK-
Ministerium für Wirtschaft, Industrie, Klimaschutz und Energie des Landes NRW
Konferenz
International Workshop on Visual Analytics 2022
DOI
10.2312/eurova.20221071
File(s)
001-005.pdf (1.03 MB)
Language
English
google-scholar
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Tags
  • Visual Analytics

  • AI

  • Deep Neural Networks

  • Trustworthy AI

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