Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

Alexander Binder, Leander Weber, Sebastian Lapuschkin, Grégoire Montavon, Klaus‐Robert Müller, Wojciech Samek

Type: Preprint

Publication Date: 2022-01-01

Citations: 0

DOI: https://doi.org/10.48550/arxiv.2211.12486

View Publication

Locations

arXiv (Cornell University) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+ PDF Chat	Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations	2023	Alexander Binder Leander Weber Sebastian Lapuschkin Grégoire Montavon Klaus‐Robert Müller Wojciech Samek
+	A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values	2018	Mukund Sundararajan Ankur Taly
+	Causal Analysis for Robust Interpretability of Neural Networks	2023	Ola Ahmad Nicolas Béreux Vahid Hashemi Freddy Lécué
+ PDF Chat	Causal Analysis for Robust Interpretability of Neural Networks	2024	Ola Ahmad Nicolas Béreux Loïc Baret Vahid Hashemi Freddy Lécué
+ PDF Chat	Robust Explainability: A tutorial on gradient-based attribution methods for deep neural networks	2022	Ian E. Nielsen Dimah Dera Ghulam Rasool Ravi P. Ramachandran Nidhal Bouaynaya
+	Precise Benchmarking of Explainable AI Attribution Methods	2023	Rafaël Brandt Daan Raatjens Georgi Gaydadjiev
+	Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey	2019	Vanessa Buhrmester David Münch Michael Arens
+ PDF Chat	Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability	2024	Joakim Edin Andreas Geert Motzfeldt Casper L. Christensen Tuukka Ruotsalo Lars Maaløe Maria Maistro
+	Better Understanding Differences in Attribution Methods via Systematic Evaluations	2023	Sukrut Rao Moritz Böhle Bernt Schiele
+ PDF Chat	Measurably Stronger Explanation Reliability Via Model Canonization	2022	Franz Motzkus Leander Weber Sebastian Lapuschkin
+	Measurably Stronger Explanation Reliability via Model Canonization	2022	Franz Motzkus Leander Weber Sebastian Lapuschkin
+ PDF Chat	Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey	2021	Vanessa Buhrmester David Münch Michael Arens
+ PDF Chat	Corrupting Neuron Explanations of Deep Visual Features	2023	Divyansh Srivastava Tuomas Oikarinen Tsui-Wei Weng
+	Corrupting Neuron Explanations of Deep Visual Features	2023	Divyansh Srivastava Tuomas Oikarinen Tsui-Wei Weng
+	On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box	2023	Yi Cai Gerhard Wunder
+ PDF Chat	Benchmarking the Attribution Quality of Vision Models	2024	Robin Hesse Simone Schaub-Meyer S. Roth
+	Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations	2020	Dan Valle Tiago Pimentel Adriano Veloso
+ PDF Chat	Assessing the Reliability of Visual Explanations of Deep Models with Adversarial Perturbations	2020	Dan Valle Tiago Pimentel Adriano Veloso
+ PDF Chat	Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation	2021	Sam Sattarzadeh Mahesh Sudhakar Anthony Lem Shervin Mehryar Konstantinos N. Plataniotis Jongseong Jang Hyunwoo Kim Yeonjeong Jeong Sangmin Lee Kyung‐Hoon Bae
+ PDF Chat	Towards Better Understanding Attribution Methods	2022	Sukrut Rao Moritz Böhle Bernt Schiele

Works That Cite This (0)

Action	Title	Year	Authors

Works Cited by This (0)

Action	Title	Year	Authors