On the stability, correctness and plausibility of visual explanation methods based on feature importance

Author:

Xu-Darme Romain1ORCID,Benois-Pineau Jenny2ORCID,Giot Romain2ORCID,Quénot Georges3ORCID,Chihani Zakaria4ORCID,Rousset Marie-Christine3ORCID,Zhukov Alexey2ORCID

Affiliation:

1. Université Paris-Saclay, CEA, List, FR and Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, France

2. LaBRI UMR CNRS 5800, Université de Bordeaux, FR

3. Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, FR

4. Université Paris-Saclay, CEA, List, FR

Funder

TRUMPET

TAILOR

GIS Albatros

Miai@Grenoble Alpes

Publisher

ACM

Reference33 articles.

1. Chirag Agarwal Nari Johnson Martin Pawelczyk Satyapriya Krishna Eshika Saxena Marinka Zitnik and Himabindu Lakkaraju. 2022. Rethinking Stability for Attribution-based Explanations. arxiv:2203.06877 [cs.LG] Chirag Agarwal Nari Johnson Martin Pawelczyk Satyapriya Krishna Eshika Saxena Marinka Zitnik and Himabindu Lakkaraju. 2022. Rethinking Stability for Attribution-based Explanations. arxiv:2203.06877 [cs.LG]

2. David Alvarez Melis and Tommi Jaakkola . 2018. Towards Robust Interpretability with Self-Explaining Neural Networks . In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.). Vol. 31. Curran Associates , Inc .https://proceedings.neurips.cc/paper_files/paper/ 2018 /file/3e9f0fc9b2f89e043bc6233994dfcf76-Paper.pdf David Alvarez Melis and Tommi Jaakkola. 2018. Towards Robust Interpretability with Self-Explaining Neural Networks. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.). Vol. 31. Curran Associates, Inc.https://proceedings.neurips.cc/paper_files/paper/2018/file/3e9f0fc9b2f89e043bc6233994dfcf76-Paper.pdf

3. Review of white box methods for explanations of convolutional neural networks in image classification tasks

4. J. Benois-Pineau R. Bourqui D. Petkovic and G. Quenot. 2023. Explainable Deep Learning AI: Methods and Challenges. Elsevier Science. https://books.google.fr/books?id=WHt5EAAAQBAJ J. Benois-Pineau R. Bourqui D. Petkovic and G. Quenot. 2023. Explainable Deep Learning AI: Methods and Challenges. Elsevier Science. https://books.google.fr/books?id=WHt5EAAAQBAJ

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3