CRAFT: Concept Recursive Activation FacTorization for Explainability

17 November 2022

Papers citing "CRAFT: Concept Recursive Activation FacTorization for Explainability"

21 / 21 papers shown

Title
Representational Similarity via Interpretable Visual Concepts Neehar Kondapaneni Oisin Mac Aodha Pietro Perona DRL 389 1 0 19 Mar 2025
Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models Itay Benou Tammy Riklin-Raviv 92 1 0 27 Feb 2025
Explaining the Impact of Training on Vision Models via Activation Clustering Ahcène Boubekki Samuel G. Fadel Sebastian Mair 162 0 0 29 Nov 2024
Restyling Unsupervised Concept Based Interpretable Networks with Generative Models Jayneel Parekh Quentin Bouniot Pavlo Mozharovskyi A. Newson Florence dÁlché-Buc SSL 89 1 0 01 Jul 2024
Toy Models of Superposition Nelson Elhage Tristan Hume Catherine Olsson Nicholas Schiefer T. Henighan ... Sam McCandlish Jared Kaplan Dario Amodei Martin Wattenberg C. Olah AAML MILM 148 351 0 21 Sep 2022
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure Paul Novello Thomas Fel David Vigouroux FAtt 40 28 0 13 Jun 2022
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence Frederik Pahde Maximilian Dreyer Leander Weber Moritz Weckbecker Christopher J. Anders Thomas Wiegand Wojciech Samek Sebastian Lapuschkin 91 9 0 07 Feb 2022
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI Alon Jacovi Ana Marasović Tim Miller Yoav Goldberg 281 436 0 15 Oct 2020
Prevalence of Neural Collapse during the terminal phase of deep learning training Vardan Papyan Xuemei Han D. Donoho 88 563 0 18 Aug 2020
RISE: Randomized Input Sampling for Explanation of Black-box Models Vitali Petsiuk Abir Das Kate Saenko FAtt 107 1,159 0 19 Jun 2018
Interpretable Explanations of Black Boxes by Meaningful Perturbation Ruth C. Fong Andrea Vedaldi FAtt AAML 45 1,514 0 11 Apr 2017
Learning Important Features Through Propagating Activation Differences Avanti Shrikumar Peyton Greenside A. Kundaje FAtt 119 3,848 0 10 Apr 2017
Axiomatic Attribution for Deep Networks Mukund Sundararajan Ankur Taly Qiqi Yan OOD FAtt 108 5,920 0 04 Mar 2017
Identity Mappings in Deep Residual Networks Kaiming He Xinming Zhang Shaoqing Ren Jian Sun 274 10,149 0 16 Mar 2016
Learning Deep Features for Discriminative Localization Bolei Zhou A. Khosla Àgata Lapedriza A. Oliva Antonio Torralba SSL SSeg FAtt 155 9,266 0 14 Dec 2015
A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorization Kejun Huang N. Sidiropoulos A. Liavas 30 171 0 13 Jun 2015
Striving for Simplicity: The All Convolutional Net Jost Tobias Springenberg Alexey Dosovitskiy Thomas Brox Martin Riedmiller FAtt 166 4,653 0 21 Dec 2014
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 272 15,825 0 12 Nov 2013
Asymptotic normality and efficiency of two Sobol index estimators Alexandre Janon T. Klein Agnès Lagnoux-Renaudie M. Nodet Clémentine Prieur 42 230 0 26 Mar 2013
Algorithms for nonnegative matrix factorization with the beta-divergence Cédric Févotte Jérôme Idier 78 802 0 08 Oct 2010
Calculations of Sobol indices for the Gaussian process metamodel A. Marrel Bertrand Iooss Béatrice Laurent O. Roustant 133 335 0 07 Feb 2008