Automation of Explainability Auditing for Image Recognition

Duleep Rathgamage Don, Jonathan Boardman, Sudhashree Sayenju, Ramazan Aygun, Yifan Zhang, Bill Franks, Sereres Johnston, George Lee, Dan Sullivan and Girish Modgil
Additional contact information
Duleep Rathgamage Don: Kennesaw State University, USA
Jonathan Boardman: Kennesaw State University, USA
Sudhashree Sayenju: Kennesaw State University, USA
Ramazan Aygun: Kennesaw State University, USA
Yifan Zhang: Kennesaw State University, USA
Bill Franks: Kennesaw State University, USA
Sereres Johnston: The Travelers Companies, Inc., USA
George Lee: The Travelers Companies, Inc., USA
Dan Sullivan: The Travelers Companies, Inc., USA
Girish Modgil: The Travelers Companies, Inc., USA

International Journal of Multimedia Data Engineering and Management (IJMDEM), 2023, vol. 14, issue 1, 1-17

Abstract: XAI requires artificial intelligence systems to provide explanations for their decisions and actions for review. Nevertheless, for big data systems where decisions are made frequently, it is technically impossible to have an expert monitor every decision. To solve this problem, the authors propose an explainability auditing method for image recognition whether the explanations are relevant for the decision made by a black box model, and involve an expert as needed when explanations are doubtful. The explainability auditing system classifies explanations as weak or satisfactory using a local explainability model by analyzing the image segments that impacted the decision. This version of the proposed method uses LIME to generate the local explanations as superpixels. Then a bag of image patches is extracted from the superpixels to determine their texture and evaluate the local explanations. Using a rooftop image dataset, the authors show that 95.7% of the cases to be audited can be detected by the proposed method.

Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJMDEM.332882 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jmdem0:v:14:y:2023:i:1:p:1-17

Access Statistics for this article

International Journal of Multimedia Data Engineering and Management (IJMDEM) is currently edited by Chengcui Zhang

More articles in International Journal of Multimedia Data Engineering and Management (IJMDEM) from IGI Global
Bibliographic data for series maintained by Journal Editor ().