Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations-Reference-Cited by-同舟云学术

Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations

Published:2024-06-03 Issue: Volume:24 Page:1-19
ISSN:
Container-title:The 2024 ACM Conference on Fairness, Accountability, and Transparency
language:
Short-container-title:

Author:

Fresz Benjamin¹^ORCID,Lörcher Lena²^ORCID,Huber Marco¹^ORCID

Affiliation:

1. Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Germany and Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Germany

2. Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Germany

Funder

Bundesministerium für Wirtschaft und Klimaschutz

Fraunhofer-Gesellschaft

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3630106.3658537

Reference40 articles.

1. Wendy Kan Addison Howard Eunbyung Park. 2018. ImageNet Object Localization Challenge. https://kaggle.com/competitions/imagenet-object-localization-challenge

2. Chirag Agarwal Satyapriya Krishna Eshika Saxena Martin Pawelczyk Nari Johnson Isha Puri Marinka Zitnik and Himabindu Lakkaraju. 2023. OpenXAI: Towards a Transparent Evaluation of Model Explanations. arxiv:2206.11104 [cs.LG]

3. Shideh Shams Amiri Rosina O. Weber Prateek Goel Owen Brooks Archer Gandley Brian Kitchell and Aaron Zehm. 2020. Data Representing Ground-Truth Explanations to Evaluate XAI Methods. arxiv:2011.09892 [cs.LG]

4. Anna Arias-Duart, Ettore Mariotti, Darío García-Gasulla, and Jose Maria Alonso-Moral. 2023. A Confusion Matrix for Evaluating Feature Attribution Methods. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023), 3709–3714. https://api.semanticscholar.org/CorpusID:260910875