Towards Better Understanding Attribution Methods

20 May 2022

Bernt Schiele

Papers citing "Towards Better Understanding Attribution Methods"

23 / 23 papers shown

Title
Now you see me! A framework for obtaining class-relevant saliency maps Nils Philipp Walter Jilles Vreeken Jonas Fischer FAtt 110 0 0 10 Mar 2025
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable Shreyash Arya Sukrut Rao Moritz Bohle Bernt Schiele 187 3 0 28 Jan 2025
Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations Benjamin Frész Lena Lörcher Marco F. Huber 64 5 0 07 Jun 2024
Parallel Backpropagation for Shared-Feature Visualization Alexander Lappe Anna Bognár Ghazaleh Ghamkhari Nejad A. Mukovskiy Lucas M. Martini Martin A. Giese Rufin Vogels FAtt 55 1 0 16 May 2024
$Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions$ Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions Fan Wang Adams Wai-Kin Kong 71 2 0 10 May 2024
Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attribution Methods Peiyu Yang Naveed Akhtar Jiantong Jiang Ajmal Mian XAI 73 2 0 02 May 2024
Smooth Deep Saliency Rudolf Herdt Maximilian Schmidt Daniel Otero Baguer Peter Maass MedIm FAtt 34 0 0 02 Apr 2024
Red-Teaming Segment Anything Model K. Jankowski Bartlomiej Sobieski Mateusz Kwiatkowski J. Szulc Michael F. Janik Hubert Baniecki P. Biecek VLM AAML 75 3 0 02 Apr 2024
What Sketch Explainability Really Means for Downstream Tasks Hmrishav Bandyopadhyay Pinaki Nath Chowdhury A. Bhunia Aneeshan Sain Tao Xiang Yi-Zhe Song 101 4 0 14 Mar 2024
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods Robin Hesse Simone Schaub-Meyer Stefan Roth AAML 86 34 0 11 Aug 2023
Saliency strikes back: How filtering out high frequencies improves white-box explanations Sabine Muzellec Thomas Fel Victor Boutin Léo Andéol R. V. Rullen Thomas Serre FAtt 73 1 0 18 Jul 2023
B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers Moritz D Boehle Navdeeppal Singh Mario Fritz Bernt Schiele 163 27 0 19 Jun 2023
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization Thomas Fel Thibaut Boissin Victor Boutin Agustin Picard Paul Novello ... Drew Linsley Tom Rousseau Rémi Cadène Laurent Gardes Thomas Serre FAtt 92 22 0 11 Jun 2023
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation Thomas Fel Victor Boutin Mazda Moayeri Rémi Cadène Louis Bethune Léo Andéol Mathieu Chalvidal Thomas Serre FAtt 97 64 0 11 Jun 2023
Don't trust your eyes: on the (un)reliability of feature visualizations Robert Geirhos Roland S. Zimmermann Blair Bilodeau Wieland Brendel Been Kim FAtt OOD 125 31 0 07 Jun 2023
Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability Soyoun Won Sung-Ho Bae Seong Tae Kim 83 2 0 26 Mar 2023
Better Understanding Differences in Attribution Methods via Systematic Evaluations Sukrut Rao Moritz D Boehle Bernt Schiele XAI 93 4 0 21 Mar 2023
Neural Insights for Digital Marketing Content Design F. Kong Yuan Li Houssam Nassif Tanner Fiez Ricardo Henao Shreya Chakrabarti 3DV 64 12 0 02 Feb 2023
A Survey of Explainable AI in Deep Visual Modeling: Methods and Metrics Naveed Akhtar XAI VLM 72 7 0 31 Jan 2023
SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report] Hamed Ayoobi Nico Potyka Francesca Toni 42 19 0 23 Jan 2023
Opti-CAM: Optimizing saliency maps for interpretability Hanwei Zhang Felipe Torres R. Sicre Yannis Avrithis Stéphane Ayache 119 27 0 17 Jan 2023
Evaluating Feature Attribution Methods for Electrocardiogram J. Suh Jimyeong Kim Euna Jung Wonjong Rhee FAtt 50 2 0 23 Nov 2022
"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Tulio Ribeiro Sameer Singh Carlos Guestrin FAtt FaML 1.3K 17,225 0 16 Feb 2016