Options
Titel
ScrutinAI: A visual analytics tool supporting semantic assessments of object detection models
Titel Supplements
Special Section on EuroVA 2022
Datum
2023-06-16
Journal
Journal | Volume | Page | Page |
|
114
|
265
|
275
|
ISSN
0097-8493
DOI
10.1016/j.cag.2023.06.010
Project(s)
Zertifizierte KI
KI-Absicherung
Akronym
Language
en
Publikationstyp
journal article
Handle
https://publica.fraunhofer.de/handle/publica/445688
Abstract
We present ScrutinAI, a Visual Analytics tool to leverage semantic understanding for deep neural network (DNN) prediction 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 uncovering and mitigating data- and model-inherent shortcomings. Our approach helps analysts and/or auditors use their semantic understanding to identify and investigate potential weaknesses in DNN models. ScrutinAI includes interactive visualizations of the model’s inputs and outputs, interactive plots with linked brushing, data filtering with textual queries on descriptive meta data and an interactive similarity based image retrieval feature. The different views and data filtering options enable global and local inspection of DNN predictions. Overall, 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 the generation of a safety argumentation for AI applications. We present two case studies on the investigation of DNN models for pedestrian detection from the automotive domain.
Schlagwort
Visual analytics
;
Human-centered machine learning
;
Deep neural networks
;
Trustworthy AI
;
Transparency
DDC
DDC::000 Informatik, Informationswissenschaft, allgemeine Werke::000 Informatik, Wissen, Systeme::004 Datenverarbeitung; Informatik
Abteilung
KD