py_ciu_image: A Python Library for Explaining Image Classification with Contextual Importance and Utility

Contextual Importance and Utility (CIU) is a model-agnostic method for explaining outcomes of AI systems. CIU has succeeded in producing meaningful explanations where state-of-the-art methods fail, e.g. for detecting bleeding in gastroenterological images. This paper presents a Python implementation...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Främling, Kary, Apopei, Ioan-Vlad, Pihlgren, Gustav Grund, Malhi, Avleen
Format: Buchkapitel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Contextual Importance and Utility (CIU) is a model-agnostic method for explaining outcomes of AI systems. CIU has succeeded in producing meaningful explanations where state-of-the-art methods fail, e.g. for detecting bleeding in gastroenterological images. This paper presents a Python implementation of CIU for explaining image classifications.
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-031-70074-3_10