A Note about: Local Explanation Methods for Deep Neural Networks lack
Sensitivity to Parameter Values

A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values

11 June 2018

Mukund Sundararajan

Ankur Taly

ArXiv (abs)PDF HTML

Papers citing "A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values"

13 / 13 papers shown

Title
Tangentially Aligned Integrated Gradients for User-Friendly ExplanationsIrish Conference on Artificial Intelligence and Cognitive Science (AICS), 2025 Lachlan Simpson Federico Costanza Kyle Millar A. Cheng Cheng-Chew Lim Hong-Gunn Chew FAtt 272 5 0 11 Mar 2025
From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation Kristoffer Wickstrøm Marina M.-C. Höhne Anna Hedström AAML 356 5 0 07 Dec 2024
Expected Grad-CAM: Towards gradient faithfulness Vincenzo Buono Peyman Sheikholharam Mashhadi M. Rahat Prayag Tiwari Stefan Byttner FAtt 207 3 0 03 Jun 2024
A Fresh Look at Sanity Checks for Saliency Maps Anna Hedström Leander Weber Sebastian Lapuschkin Marina M.-C. Höhne FAtt LRM 260 11 0 03 May 2024
Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test Anna Hedström Leander Weber Sebastian Lapuschkin Marina M.-C. Höhne LRM 205 10 0 12 Jan 2024
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus Anna Hedström P. Bommer Kristoffer K. Wickstrom Wojciech Samek Sebastian Lapuschkin Marina M.-C. Höhne 280 27 0 14 Feb 2023
Towards Improved Input Masking for Convolutional Neural NetworksIEEE International Conference on Computer Vision (ICCV), 2022 S. Balasubramanian Soheil Feizi AAML 200 7 0 26 Nov 2022
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network ExplanationsComputer Vision and Pattern Recognition (CVPR), 2022 Alexander Binder Leander Weber Sebastian Lapuschkin G. Montavon Klaus-Robert Muller Wojciech Samek FAtt AAML 156 31 0 22 Nov 2022
Comparing Baseline Shapley and Integrated Gradients for Local Explanation: Some Additional Insights Tianshu Feng Zhipu Zhou Tarun Joshi V. Nair FAtt 178 6 0 12 Aug 2022
GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation BaselinesInternational Conference on Machine Learning (ICML), 2020 Sheng-Min Shih Pin-Ju Tien Zohar Karnin FAtt 289 16 0 11 Nov 2020
Explaining Explanations: Axiomatic Feature Interactions for Deep NetworksJournal of machine learning research (JMLR), 2020 Joseph D. Janizek Pascal Sturmfels Su-In Lee FAtt 638 167 0 10 Feb 2020
XRAI: Better Attributions Through RegionsIEEE International Conference on Computer Vision (ICCV), 2019 A. Kapishnikov Tolga Bolukbasi Fernanda Viégas Michael Terry FAtt XAI 188 242 0 06 Jun 2019
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values Julius Adebayo Justin Gilmer Ian Goodfellow Been Kim FAtt AAML 177 130 0 08 Oct 2018