XRAI: Better Attributions Through Regions

Andrei Kapishnikov, Tolga Bolukbasi, Fernanda Viégas, Michael Terry

Type: Preprint

Publication Date: 2019-06-06

Citations: 7

Locations

arXiv (Cornell University) - View

Similar Works

Action	Title	Year	Authors
+ PDF Chat	XRAI: Better Attributions Through Regions	2019	Andrei Kapishnikov Tolga Bolukbasi Fernanda Viégas Michael Terry
+	XRAI: Better Attributions Through Regions	2019	Andrei Kapishnikov Tolga Bolukbasi Fernanda Viégas Michael Terry
+ PDF Chat	COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification	2023	Rangel Daroya Aaron Sun Subhransu Maji
+	COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification	2023	Rangel Daroya Aaron Sun Subhransu Maji
+	The (Un)reliability of saliency methods	2017	Pieter-Jan Kindermans Sara Hooker Julius Adebayo Maximilian Alber Kristof T. Schütt Sven Dähne Dumitru Erhan Been Kim
+	Efficient Saliency Maps for Explainable AI	2019	T. Nathan Mundhenk Barry Y. Chen Gerald Friedland
+ PDF Chat	Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations	2024	Benjamin Frész Lena Lörcher Marco F. Huber
+	A Simple Saliency Method That Passes the Sanity Checks	2019	Arushi Gupta Sanjeev Arora
+	Believe The HiPe: Hierarchical Perturbation for Fast, Robust, and Model-Agnostic Saliency Mapping	2021	Jessica Cooper Ognjen Arandjelović David J. Harrison
+	Sanity Simulations for Saliency Methods.	2021	Joon Sik Kim Gregory Plumb Ameet Talwalkar
+	Opti-CAM: Optimizing saliency maps for interpretability	2023	Hanwei Zhang Felipe Torres Ronan Sicre Yannis Avrithis Stéphane Ayache
+	Opti-Cam: Optimizing Saliency Maps for Interpretability	2023	Hanwei Zhang Felipe Torres Ronan Sicre Yannis Avrithis Stéphane Ayache
+	Opti-CAM: Optimizing saliency maps for interpretability	2024	Hanwei Zhang Felipe Torres Ronan Sicre Yannis Avrithis Stéphane Ayache
+	Sanity Simulations for Saliency Methods	2021	Joon Sik Kim Gregory Plumb Ameet Talwalkar
+	Believe the HiPe: Hierarchical perturbation for fast, robust, and model-agnostic saliency mapping	2022	Jessica Cooper Ognjen Arandjelović David J. Harrison
+	Input Bias in Rectified Gradients and Modified Saliency Maps	2020	Lennart Brocki Neo Christopher Chung
+	Input Bias in Rectified Gradients and Modified Saliency Maps	2020	Lennart Brocki Neo Christopher Chung
+	New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound	2022	Arushi Gupta Nikunj Saunshi Dingli Yu Kaifeng Lyu Sanjeev Arora
+ PDF Chat	Input Bias in Rectified Gradients and Modified Saliency Maps	2021	Lennart Brocki Neo Christopher Chung
+	Quantitative Evaluations on Saliency Methods: An Experimental Study	2020	Xiaohui Li Yuhan Shi Haoyang Li Wei Bai Yuanwei Song Caleb Chen Cao Lei Chen

Works That Cite This (5)

Action	Title	Year	Authors
+	Explaining Explanations: Axiomatic Feature Interactions for Deep Networks	2020	Joseph D. Janizek Pascal Sturmfels Su‐In Lee
+	There and Back Again: Revisiting Backpropagation Saliency Methods	2020	Sylvestre-Alvise Rebuffi Ruth Fong Xu Ji Andrea Vedaldi
+	A Baseline for Shapley Values in MLPs: from Missingness to Neutrality	2020	Cosimo Izzo Aldo Lipani Ramin Okhrati Francesca Medda
+	A Game-Theoretic Taxonomy of Visual Concepts in DNNs	2021	Xu Cheng Chuntung Chu Yi Zheng Jie Ren Quanshi Zhang
+	Facial Expression Recognition with Deep Learning	2020	Amil Khanzada Charles Bai Ferhat Turker Celepcikay

Works Cited by This (23)

Action	Title	Year	Authors
+ PDF Chat	ImageNet Large Scale Visual Recognition Challenge	2015	Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael S. Bernstein
+	How to Explain Individual Classification Decisions	2009	David Baehrens Timon Schroeter Stefan Harmeling Motoaki Kawanabe Katja Hansen Klaus‐Robert Müller
+ PDF Chat	Deep Residual Learning for Image Recognition	2016	Kaiming He Xiangyu Zhang Shaoqing Ren Jian Sun
+	Explaining nonlinear classification decisions with deep Taylor decomposition	2016	Grégoire Montavon Sebastian Lapuschkin Alexander Binder Wojciech Samek Klaus‐Robert Müller
+	Not Just a Black Box: Learning Important Features Through Propagating Activation Differences	2016	Avanti Shrikumar Peyton Greenside А.В. Щербина Anshul Kundaje
+	SmoothGrad: removing noise by adding noise	2017	Daniel Smilkov Nikhil Thorat Been Kim Fernanda Viégas Martin Wattenberg
+	Interpretation of Neural Networks is Fragile	2017	Amirata Ghorbani Abubakar Abid James Zou
+	A unified view of gradient-based attribution methods for Deep Neural Networks	2017	Marco Ancona Enea Ceolini Cengiz Öztireli Markus Groß
+	Learning how to explain neural networks: PatternNet and PatternAttribution	2017	Pieter Jan Kindermans Kristof T. Schütt Maximilian Alber K. Müller Dumitru Erhan Been Kim Sven Dähne
+ PDF Chat	Review of Visual Saliency Detection With Comprehensive Information	2018	Runmin Cong Jianjun Lei Huazhu Fu Ming‐Ming Cheng Weisi Lin Qingming Huang