Unmasking Clever Hans Predictors and Assessing What Machines Really Learn

Nature Communications (Nat Commun), 2019

26 February 2019

Papers citing "Unmasking Clever Hans Predictors and Assessing What Machines Really Learn"

50 / 382 papers shown

Title
On the Foundations of Shortcut LearningInternational Conference on Learning Representations (ICLR), 2023 Katherine Hermann Hossein Mobahi Thomas Fel M. C. Mozer VLM 361 57 0 24 Oct 2023
Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI Oliver Eberle Jochen Büttner Hassan el-Hajj G. Montavon Klaus-Robert Muller Matteo Valleriani 141 4 0 13 Oct 2023
Impact of Label Types on Training SWIN Models with Overhead Imagery Ryan Ford Kenneth Hutchison Nicholas Felts Benjamin Cheng Jesse Lew Kyle Jackson 151 0 0 11 Oct 2023
Human-Centered Evaluation of XAI Methods Karam Dawoud Wojciech Samek Peter Eisert Sebastian Lapuschkin Sebastian Bosse 137 6 0 11 Oct 2023
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation Sidney Bender Christopher J. Anders Pattarawat Chormai Heike Marxfeld J. Herrmann G. Montavon CML 190 5 0 02 Oct 2023
Targeted Activation Penalties Help CNNs Ignore Spurious SignalsAAAI Conference on Artificial Intelligence (AAAI), 2023 Dekai Zhang Hamed Ayoobi Francesca Toni AAML 185 3 0 22 Sep 2023
Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future Metrics Patricio Vera Pedro Moya Lisa Barraza ELM 201 2 0 21 Sep 2023
Mitigating Shortcuts in Language Models with Soft Label EncodingInternational Conference on Language Resources and Evaluation (LREC), 2023 Zirui He Huiqi Deng Haiyan Zhao Ninghao Liu Jundong Li 120 2 0 17 Sep 2023
Insights Into the Inner Workings of Transformer Models for Protein Function PredictionBioinformatics (Bioinformatics), 2023 M. Wenzel Erik Grüner Nils Strodthoff ViT 175 13 0 07 Sep 2023
i-Align: an interpretable knowledge graph alignment modelData mining and knowledge discovery (DMKD), 2023 Bayu Distiawan Trisedya Flora D. Salim Jeffrey Chan Damiano Spina Falk Scholer Mark Sanderson 148 11 0 26 Aug 2023
Measuring Spurious Correlation in Classification: 'Clever Hans' in TranslationeseRecent Advances in Natural Language Processing (RANLP), 2023 Angana Borah Daria Pylypenko C. España-Bonet Josef van Genabith 84 6 0 25 Aug 2023
A survey on bias in machine learning research Agnieszka Mikołajczyk-Bareła M. Grochowski AI4CE FaML 257 5 0 22 Aug 2023
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent SpaceAAAI Conference on Artificial Intelligence (AAAI), 2023 Maximilian Dreyer Frederik Pahde Christopher J. Anders Wojciech Samek Sebastian Lapuschkin AI4CE 164 18 0 18 Aug 2023
On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-boxInternational Conference on Machine Learning (ICML), 2023 Yingcheng Cai Gerhard Wunder FAtt 111 3 0 18 Aug 2023
Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI) Barnaby Crook Maximilian Schluter Timo Speith 153 27 0 26 Jul 2023
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems Saddek Bensalem Chih-Hong Cheng Wei Huang Xiaowei Huang Changshun Wu Xingyu Zhao AAML 213 10 0 20 Jul 2023
Interpreting and Correcting Medical Image Classification with PIP-Net Meike Nauta J. H. Hegeman J. Geerdink Jorg Schlotterer M. V. Keulen Christin Seifert MedIm 131 15 0 19 Jul 2023
What do neural networks learn in image classification? A frequency shortcut perspectiveIEEE International Conference on Computer Vision (ICCV), 2023 Shunxin Wang Raymond N. J. Veldhuis Christoph Brune N. Strisciuglio 159 36 0 19 Jul 2023
A Vulnerability of Attribution Methods Using Pre-Softmax Scores Miguel A. Lerma Mirtha Lucas FAtt 206 0 0 06 Jul 2023
Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative WorkInteracción (HCI), 2023 Sabine Theis Sophie F. Jentzsch Fotini Deligiannaki C. Berro A. Raulf C. Bruder 154 13 0 27 Jun 2023
Improving neural network representations using human similarity judgmentsNeural Information Processing Systems (NeurIPS), 2023 Lukas Muttenthaler Lorenz Linhardt Jonas Dippel Robert A. Vandermeulen Katherine L. Hermann Andrew Kyle Lampinen Simon Kornblith 267 41 0 07 Jun 2023
Hardness of Deceptive Certificate Selection Stephan Wäldchen AAML 132 1 0 07 Jun 2023
Using Multiple Dermoscopic Photographs of One Lesion Improves Melanoma Classification via Deep Learning: A Prognostic Diagnostic Accuracy StudyJournal of American Academy of Dermatology (JAAD), 2023 A. Hekler Roman C. Maron Sarah Haggenmuller Max Schmitt Christoph Wies ... Matthias Goebeler Bastian Schilling Jakob N. Kather E. Krieghoff-Henning T. Brinker 112 5 0 05 Jun 2023
Theoretical Behavior of XAI Methods in the Presence of Suppressor VariablesInternational Conference on Machine Learning (ICML), 2023 Rick Wilming Leo Kieslich Benedict Clark Stefan Haufe 115 12 0 02 Jun 2023
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning ShortcutsNeural Information Processing Systems (NeurIPS), 2023 Emanuele Marconato Stefano Teso Antonio Vergari Baptiste Caramiaux 282 52 0 31 May 2023
Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery Patrick Wagner Temesgen Mehari Wilhelm Haverkamp Nils Strodthoff 203 26 0 26 May 2023
Reliability Scores from Saliency Map Clusters for Improved Image-based Harvest-Readiness Prediction in CauliflowerIEEE Geoscience and Remote Sensing Letters (GRSL), 2023 Jana Kierdorf R. Roscher 96 9 0 24 May 2023
A Probabilistic Transformation of Distance-Based OutliersMachine Learning and Knowledge Extraction (MLKE), 2023 David Muhr M. Affenzeller Josef Küng 165 15 0 16 May 2023
The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain A. Moskvichev Victor Vikram Odouard Melanie Mitchell 177 98 0 11 May 2023
A Survey on the Robustness of Computer Vision Models against Common Corruptions Shunxin Wang Raymond N. J. Veldhuis Christoph Brune N. Strisciuglio OOD VLM 455 21 0 10 May 2023
Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces Georgii Mikriukov Gesina Schwalbe Christian Hellert Korinna Bade 140 3 0 30 Apr 2023
One Explanation Does Not Fit XIL Felix Friedrich David Steinmann Kristian Kersting LRM 194 3 0 14 Apr 2023
Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy David Schlangen ELM 146 17 0 14 Apr 2023
Preemptively Pruning Clever-Hans Strategies in Deep Neural NetworksInformation Fusion (Inf. Fusion), 2023 Lorenz Linhardt Klaus-Robert Muller G. Montavon AAML 282 9 0 12 Apr 2023
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary TasksPattern Recognition (Pattern Recogn.), 2023 Yi Li Hualiang Wang Yiqun Duan Xuelong Li VLM MedIm AAML 83 69 0 12 Apr 2023
How good Neural Networks interpretation methods really are? A quantitative benchmark Antoine Passemiers Pietro Folco D. Raimondi G. Birolo Yves Moreau P. Fariselli FAtt 108 2 0 05 Apr 2023
Neglected Free Lunch -- Learning Image Classifiers Using Annotation ByproductsIEEE International Conference on Computer Vision (ICCV), 2023 Dongyoon Han Junsuk Choe Dante Chun John Joon Young Chung Minsuk Chang Sangdoo Yun Jean Y. Song Seong Joon Oh OOD 1.3K 4 1 30 Mar 2023
Problems and shortcuts in deep learning for screening mammography Trevor Tsue Brent Mombourquette Ahmed Taha Thomas P. Matthews Yen Nhi Truong Vu Jason Su 94 1 0 29 Mar 2023
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep ModelsInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023 Frederik Pahde Maximilian Dreyer Wojciech Samek Sebastian Lapuschkin 133 22 0 22 Mar 2023
Mark My Words: Dangers of Watermarked Images in ImageNet Kirill Bykov Klaus-Robert Muller Marina M.-C. Höhne 137 7 0 09 Mar 2023
Towards Trustable Skin Cancer Diagnosis via Rewriting Model's DecisionComputer Vision and Pattern Recognition (CVPR), 2023 Siyuan Yan Zhen Yu Xuelin Zhang Dwarikanath Mahapatra Shekhar S. Chandra Monika Janda Peter Soyer Z. Ge 182 34 0 02 Mar 2023
Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate ScienceArtificial Intelligence for the Earth Systems (AI4ES), 2023 P. Bommer M. Kretschmer Anna Hedström Dilyara Bareeva Marina M.-C. Höhne 286 49 0 01 Mar 2023
On the contribution of pre-trained models to accuracy and utility in modeling distributed energy resources H. Kazmi Pierre Pinson 121 0 0 22 Feb 2023
SpecXAI -- Spectral interpretability of Deep Learning Models Stefan Druc Peter Wooldridge A. Krishnamurthy Soumik Sarkar Aditya Balu 137 0 0 20 Feb 2023
On The Coherence of Quantitative Evaluation of Visual ExplanationsComputer Vision and Image Understanding (CVIU), 2023 Benjamin Vandersmissen José Oramas XAI FAtt 314 6 0 14 Feb 2023
Shortcut Detection with Variational AutoencodersIEEE International Joint Conference on Neural Network (IJCNN), 2023 Nicolas Müller Simon Roschmann Shahbaz Khan Philip Sperl Konstantin Böttinger AAML DRL 183 2 0 08 Feb 2023
Understanding User Preferences in Explainable Artificial Intelligence: A Survey and a Mapping Function ProposalACM Transactions on Intelligent Systems and Technology (ACM TIST), 2023 M. Hashemi Ali Darejeh Francisco Cruz 289 4 0 07 Feb 2023
Cluster-CAM: Cluster-Weighted Visual Interpretation of CNNs' Decision in Image ClassificationNeural Networks (Neural Netw.), 2023 Zhenpeng Feng H. Ji M. Daković Xiyang Cui Mingzhe Zhu Ljubisa Stankovic 153 11 0 03 Feb 2023
Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexityInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Vincent Souveton Arnaud Guillin J. Jasche G. Lavaux Manon Michel 196 3 0 03 Feb 2023
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept RehearsalInternational Conference on Machine Learning (ICML), 2023 Emanuele Marconato G. Bontempo E. Ficarra Simone Calderara Baptiste Caramiaux Stefano Teso NAI LRM CLL 172 29 0 02 Feb 2023

All Papers

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn

Papers citing "Unmasking Clever Hans Predictors and Assessing What Machines Really Learn"