Sebastian Lapuschkin

138 papers A* 7B 5C 2Misc 1Journal 99Unranked 18
YearRankTypeTitle / Venue / Authors
2026 J jnl
Building Trust in PINNs: Error Estimation through Finite Difference Methods.
CoRR
Aleksander Krasowski, René P. Klausen, Aycan Celik, Sebastian Lapuschkin, Wojciech Samek, Jonas R. Naujoks
2026 J jnl
Concept-based explanations of Segmentation and Detection models in Natural Disaster Management.
CoRR
Samar Heydari, Jawher Said, Galip Ümit Yolcu, Evgenii Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios Mygdalis, Ioannis Pitas, Sebastian Lapuschkin, Leila Arras
2026 J jnl
Deep learning-based multi project InP wafer simulation towards unsupervised surface defect detection.
J. Frankl. Inst.
Emílio Dolgener Cantú, Rolf Klemens Wittmann, Oliver Abdeen, Patrick Wagner, Wojciech Samek, Moritz Baier, Sebastian Lapuschkin
2026 J jnl
Structural Compactness as a Complementary Criterion for Explanation Quality.
CoRR
Mohammad Mahdi Mesgari, Jackie Ma, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
2026 J jnl
X-SYS: A Reference Architecture for Interactive Explanation Systems.
CoRR
Tobias Labarta, Nhi Hoang, Maximilian Dreyer, Jim Berend, Oleg Hein, Jackie Ma, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
A Close Look at Decomposition-based XAI-Methods for Transformer Language Models.
CoRR
Leila Arras, Bruno Puri, Patrick Kahardipraja, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
ASIDE: Architectural Separation of Instructions and Data in Language Models.
CoRR
Egor Zverev, Evgenii Kortukov, Alexander Panfilov, Soroush Tabesh, Alexandra Volkova, Sebastian Lapuschkin, Wojciech Samek, Christoph H. Lampert
2025 J jnl
Atlas-Alignment: Making Interpretability Transferable Across Language Models.
CoRR
Bruno Puri, Jim Berend, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Attribution-Guided Decoding.
CoRR
Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs.
CoRR
Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Patrick Kahardipraja, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Circuit Insights: Towards Interpretability Beyond Activations.
CoRR
Elena Golimblevskaia, Aakriti Jain, Bruno Puri, Ammar Ibrahim, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection.
CoRR
Emílio Dolgener Cantú, Rolf Klemens Wittmann, Oliver Abdeen, Patrick Wagner, Wojciech Samek, Moritz Baier, Sebastian Lapuschkin
2025 J jnl
Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation.
Trans. Mach. Learn. Res.
Leander Weber, Jim Berend, Moritz Weckbecker, Alexander Binder, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Ensuring Medical AI Safety: Explainable AI-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data.
CoRR
Frederik Pahde, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Ensuring medical AI safety: interpretability-driven detection and mitigation of spurious model behavior and associated data.
Mach. Learn.
Frederik Pahde, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Evaluating Interpretable Methods via Geometric Alignment of Functional Distortions.
Trans. Mach. Learn. Res.
Anna Hedström, Philine Lou Bommer, Thomas F. Burns, Sebastian Lapuschkin, Wojciech Samek, Marina M.-C. Höhne
2025 J jnl
Explaining predictive uncertainty by exposing second-order effects.
Pattern Recognit.
Florian Bley, Sebastian Lapuschkin, Wojciech Samek, Grégoire Montavon
2025 — conf
FADE: Why Bad Descriptions Happen to Good Features.
ACL (Findings)
Bruno Puri, Aakriti Jain, Elena Golimblevskaia, Patrick Kahardipraja, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
FADE: Why Bad Descriptions Happen to Good Features.
CoRR
Bruno Puri, Aakriti Jain, Elena Golimblevskaia, Patrick Kahardipraja, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance.
CoRR
Maximilian Dreyer, Lorenz Hufe, Jim Berend, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Iterative Inference in a Chess-Playing Neural Network.
CoRR
Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek
2025 — conf
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks.
xAI (2)
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker, Galip Ümit Yolcu, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek, René P. Klausen
2025 J jnl
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks.
CoRR
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker, Galip Ümit Yolcu, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek, René P. Klausen
2025 J jnl
LieSolver: A PDE-constrained solver for IBVPs using Lie symmetries.
CoRR
René P. Klausen, Ivan Timofeev, Johannes Frank, Jonas R. Naujoks, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 J jnl
Mechanistic understanding and validation of large AI models with SemanticLens.
CoRR
Maximilian Dreyer, Jim Berend, Tobias Labarta, Johanna Vielhaben, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2025 A* conf
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence.
ICLR
Frederik Pahde, Maximilian Dreyer, Moritz Weckbecker, Leander Weber, Christopher J. Anders, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations.
CoRR
Eren Erogullari, Sebastian Lapuschkin, Wojciech Samek, Frederik Pahde
2025 — conf
Post-hoc Concept Disentanglement: From Correlated to Isolated Concept Representations.
xAI (1)
Eren Erogullari, Sebastian Lapuschkin, Wojciech Samek, Frederik Pahde
2025 J jnl
Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video.
CoRR
Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards
2025 J jnl
Relevance-driven Input Dropout: an Explanation-guided Regularization Technique.
CoRR
Shreyas Gururaj, Lars Grüne, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
2025 J jnl
See What I Mean? CUE: A Cognitive Model of Understanding Explanations.
CoRR
Tobias Labarta, Nhi Hoang, Katharina Weitz, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
2025 J jnl
Sparse, Efficient and Explainable Data Attribution with DualXDA.
Trans. Mach. Learn. Res.
Moritz Weckbecker, Galip Ümit Yolcu, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs.
CoRR
Alexander Panfilov, Evgenii Kortukov, Kristina Nikolic, Matthias Bethge, Sebastian Lapuschkin, Wojciech Samek, Ameya Prabhu, Maksym Andriushchenko, Jonas Geiping
2025 J jnl
The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation.
CoRR
Patrick Kahardipraja, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2025 J jnl
Towards Mechanistic Defenses Against Typographic Attacks in CLIP.
CoRR
Lorenz Hufe, Constantin Venhoff, Maximilian Dreyer, Sebastian Lapuschkin, Wojciech Samek
2024 — conf
A Fresh Look at Sanity Checks for Saliency Maps.
xAI (1)
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2024 J jnl
A Fresh Look at Sanity Checks for Saliency Maps.
CoRR
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2024 A* conf
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers.
ICML
Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2024 J jnl
AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers.
CoRR
Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
2024 J jnl
AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark.
J. Frankl. Inst.
Sören Becker, Johanna Vielhaben, Marcel Ackermann, Klaus-Robert Müller, Sebastian Lapuschkin, Wojciech Samek
2024 A* conf
CoSy: Evaluating Textual Explanations of Neurons.
NeurIPS
Laura Kopf, Philine Lou Bommer, Anna Hedström, Sebastian Lapuschkin, Marina M.-C. Höhne, Kirill Bykov
2024 J jnl
CoSy: Evaluating Textual Explanations of Neurons.
CoRR
Laura Kopf, Philine Lou Bommer, Anna Hedström, Sebastian Lapuschkin, Marina M.-C. Höhne, Kirill Bykov
2024 J jnl
DualView: Data Attribution from the Dual Perspective.
CoRR
Galip Ümit Yolcu, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Explainable AI for time series via Virtual Inspection Layers.
Pattern Recognit.
Johanna Vielhaben, Sebastian Lapuschkin, Grégoire Montavon, Wojciech Samek
2024 — ed.
Explainable Artificial Intelligence - Second World Conference, xAI 2024, Valletta, Malta, July 17-19, 2024, Proceedings, Part I
xAI (1)
Luca Longo, Sebastian Lapuschkin, Christin Seifert
2024 — ed.
Explainable Artificial Intelligence - Second World Conference, xAI 2024, Valletta, Malta, July 17-19, 2024, Proceedings, Part II
xAI (2)
Luca Longo, Sebastian Lapuschkin, Christin Seifert
2024 — ed.
Explainable Artificial Intelligence - Second World Conference, xAI 2024, Valletta, Malta, July 17-19, 2024, Proceedings, Part III
xAI (3)
Luca Longo, Sebastian Lapuschkin, Christin Seifert
2024 — ed.
Explainable Artificial Intelligence - Second World Conference, xAI 2024, Valletta, Malta, July 17-19, 2024, Proceedings, Part IV
xAI (4)
Luca Longo, Sebastian Lapuschkin, Christin Seifert
2024 — conf
Explainable Concept Mappings of MRI: Revealing the Mechanisms Underlying Deep Learning-Based Brain Disease Classification.
xAI (2)
Christian Tinauer, Anna Damulina, Maximilian Sackl, Martin Soellradl, Reduan Achtibat, Maximilian Dreyer, Frederik Pahde, Sebastian Lapuschkin, Reinhold Schmidt, Stefan Ropele, Wojciech Samek, Christian Langkammer
2024 J jnl
Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification.
CoRR
Christian Tinauer, Anna Damulina, Maximilian Sackl, Martin Soellradl, Reduan Achtibat, Maximilian Dreyer, Frederik Pahde, Sebastian Lapuschkin, Reinhold Schmidt, Stefan Ropele, Wojciech Samek, Christian Langkammer
2024 J jnl
Explaining Predictive Uncertainty by Exposing Second-Order Effects.
CoRR
Florian Bley, Sebastian Lapuschkin, Wojciech Samek, Grégoire Montavon
2024 A* conf
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space.
AAAI
Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
2024 A* conf
Generative Fractional Diffusion Models.
NeurIPS
Gabriel Nobis, Maximilian Springenberg, Marco Aversa, Michael Detzel, Rembert Daems, Roderick Murray-Smith, Shinichi Nakajima, Sebastian Lapuschkin, Stefano Ermon, Tolga Birdal, Manfred Opper, Christoph Knochenhauer, Luis Oala, Wojciech Samek
2024 J jnl
PINNfluence: Influence Functions for Physics-Informed Neural Networks.
CoRR
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek, René P. Klausen
2024 — conf
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits.
XAI4CV
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits.
CoRR
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers.
CoRR
Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2024 — conf
Pruning by Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers.
ECCV Workshops (21)
Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond.
CoRR
Dilyara Bareeva, Galip Ümit Yolcu, Anna Hedström, Niklas Schmolenski, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2024 — conf
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression.
CVPR Workshops
Dilyara Bareeva, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression.
CoRR
Dilyara Bareeva, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sebastian Lapuschkin
2024 J jnl
Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test.
CoRR
Anna Hedström, Leander Weber, Sebastian Lapuschkin, Marina M.-C. Höhne
2024 — conf
Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization.
ECCV Workshops (20)
Rohan Reddy Mekala, Frederik Pahde, Simon Baur, Sneha Chandrashekar, Madeline Diep, Markus Wenzel, Eric L. Wisotzky, Galip Ümit Yolcu, Sebastian Lapuschkin, Jackie Ma, Peter Eisert, Mikael Lindvall, Adam A. Porter, Wojciech Samek
2024 J jnl
Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization.
CoRR
Rohan Reddy Mekala, Frederik Pahde, Simon Baur, Sneha Chandrashekar, Madeline Diep, Markus Wenzel, Eric L. Wisotzky, Galip Ümit Yolcu, Sebastian Lapuschkin, Jackie Ma, Peter Eisert, Mikael Lindvall, Adam A. Porter, Wojciech Samek
2024 — conf
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations.
CVPR Workshops
Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin
2023 J jnl
Beyond explaining: Opportunities and challenges of XAI-based model improvement.
Inf. Fusion
Leander Weber, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek
2023 B conf
Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models.
ETRA
Daniel G. Krakowczyk, Paul Prasse, David R. Reich, Sebastian Lapuschkin, Tobias Scheffer, Lena A. Jäger
2023 J jnl
Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models.
CoRR
Daniel G. Krakowczyk, Paul Prasse, David R. Reich, Sebastian Lapuschkin, Tobias Scheffer, Lena A. Jäger
2023 J jnl
Explainable AI for Time Series via Virtual Inspection Layers.
CoRR
Johanna Vielhaben, Sebastian Lapuschkin, Grégoire Montavon, Wojciech Samek
2023 J jnl
From Hope to Safety: Unlearning Biases of Deep Models by Enforcing the Right Reasons in Latent Space.
CoRR
Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
2023 J jnl
From attribution maps to human-understandable explanations through Concept Relevance Propagation.
Nat. Mac. Intell.
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2023 J jnl
Generative Fractional Diffusion Models.
CoRR
Gabriel Nobis, Marco Aversa, Maximilian Springenberg, Michael Detzel, Stefano Ermon, Shinichi Nakajima, Roderick Murray-Smith, Sebastian Lapuschkin, Christoph Knochenhauer, Luis Oala, Wojciech Samek
2023 — conf
Human-Centered Evaluation of XAI Methods.
ICDM (Workshops)
Karam Dawoud, Wojciech Samek, Peter Eisert, Sebastian Lapuschkin, Sebastian Bosse
2023 J jnl
Human-Centered Evaluation of XAI Methods.
CoRR
Karam Dawoud, Wojciech Samek, Peter Eisert, Sebastian Lapuschkin, Sebastian Bosse
2023 J jnl
Layer-wise Feedback Propagation.
CoRR
Leander Weber, Jim Berend, Alexander Binder, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2023 — conf
Optimizing Explanations by Network Canonization and Hyperparameter Search.
CVPR Workshops
Frederik Pahde, Galip Ümit Yolcu, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin
2023 J jnl
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond.
J. Mach. Learn. Res.
Anna Hedström, Leander Weber, Daniel Krakowczyk, Dilyara Bareeva, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 — conf
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models.
MICCAI (2)
Frederik Pahde, Maximilian Dreyer, Wojciech Samek, Sebastian Lapuschkin
2023 J jnl
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models.
CoRR
Frederik Pahde, Maximilian Dreyer, Wojciech Samek, Sebastian Lapuschkin
2023 — conf
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations.
CVPR Workshops
Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2023 A* conf
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations.
CVPR
Alexander Binder, Leander Weber, Sebastian Lapuschkin, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
2023 J jnl
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus.
CoRR
Anna Hedström, Philine Lou Bommer, Kristoffer K. Wickstrøm, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 J jnl
The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantus.
Trans. Mach. Learn. Res.
Anna Hedström, Philine Lou Bommer, Kristoffer Knutsen Wickstrøm, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2023 J jnl
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations.
CoRR
Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin
2023 C conf
XAI-based Comparison of Audio Event Classifiers with different Input Representations.
CBMI
Annika Frommholz, Fabian Seipel, Sebastian Lapuschkin, Wojciech Samek, Johanna Vielhaben
2023 J jnl
XAI-based Comparison of Input Representations for Audio Event Classification.
CoRR
Annika Frommholz, Fabian Seipel, Sebastian Lapuschkin, Wojciech Samek, Johanna Vielhaben
2022 J jnl
Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement.
CoRR
Leander Weber, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek
2022 J jnl
But that's not why: Inference adjustment by interactive prototype deselection.
CoRR
Michael Gerstenberger, Sebastian Lapuschkin, Peter Eisert, Sebastian Bosse
2022 J jnl
Explain and improve: LRP-inference fine-tuning for image captioning models.
Inf. Fusion
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Alexander Binder
2022 C conf
Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI.
CD-MAKE
Sami Ede, Serop Baghdadlian, Leander Weber, An Nguyen, Dario Zanca, Wojciech Samek, Sebastian Lapuschkin
2022 J jnl
Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI.
CoRR
Sami Ede, Serop Baghdadlian, Leander Weber, An Nguyen, Dario Zanca, Wojciech Samek, Sebastian Lapuschkin
2022 J jnl
Explaining Machine Learning Models for Clinical Gait Analysis.
ACM Trans. Comput. Heal.
Djordje Slijepcevic, Fabian Horst, Sebastian Lapuschkin, Brian Horsak, Anna-Maria Raberger, Andreas Kranzl, Wojciech Samek, Christian Breiteneder, Wolfgang Immanuel Schöllhorn, Matthias Zeppelzauer
2022 J jnl
Explaining automated gender classification of human gait.
CoRR
Fabian Horst, Djordje Slijepcevic, Matthias Zeppelzauer, Anna-Maria Raberger, Sebastian Lapuschkin, Wojciech Samek, Wolfgang Immanuel Schöllhorn, Christian Breiteneder, Brian Horsak
2022 J jnl
Explaining machine learning models for age classification in human gait analysis.
CoRR
Djordje Slijepcevic, Fabian Horst, Marvin Simak, Sebastian Lapuschkin, Anna-Maria Raberger, Wojciech Samek, Christian Breiteneder, Wolfgang Immanuel Schöllhorn, Matthias Zeppelzauer, Brian Horsak
2022 J jnl
Finding and removing Clever Hans: Using explanation methods to debug and improve deep models.
Inf. Fusion
Christopher J. Anders, Leander Weber, David Neumann, Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin
2022 J jnl
From "Where" to "What": Towards Human-Understandable Explanations through Concept Relevance Propagation.
CoRR
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2022 B conf
Measurably Stronger Explanation Reliability Via Model Canonization.
ICIP
Franz Motzkus, Leander Weber, Sebastian Lapuschkin
2022 J jnl
Measurably Stronger Explanation Reliability via Model Canonization.
CoRR
Franz Motzkus, Leander Weber, Sebastian Lapuschkin
2022 J jnl
Optimizing Explanations by Network Canonization and Hyperparameter Search.
CoRR
Frederik Pahde, Galip Ümit Yolcu, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin
2022 J jnl
PatClArC: Using Pattern Concept Activation Vectors for Noise-Robust Model Debugging.
CoRR
Frederik Pahde, Leander Weber, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
2022 J jnl
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations.
CoRR
Anna Hedström, Leander Weber, Dilyara Bareeva, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, Marina M.-C. Höhne
2022 J jnl
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations.
CoRR
Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
2022 — conf
Selection of XAI Methods Matters: Evaluation of Feature Attribution Methods for Oculomotoric Biometric Identification.
Gaze Meets ML
Daniel Krakowczyk, David R. Reich, Paul Prasse, Sebastian Lapuschkin, Tobias Scheffer, Lena A. Jäger
2022 J jnl
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations.
CoRR
Alexander Binder, Leander Weber, Sebastian Lapuschkin, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
2022 J jnl
Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain.
NeuroImage
Simon M. Hofmann, Frauke Beyer, Sebastian Lapuschkin, Ole Goltermann, Markus Loeffler, Klaus-Robert Müller, Arno Villringer, Wojciech Samek, Anja Veronica Witte
2021 J jnl
ECQ
CoRR
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
2021 J jnl
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications.
Proc. IEEE
Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin, Christopher J. Anders, Klaus-Robert Müller
2021 J jnl
Pruning by explaining: A novel criterion for deep neural network pruning.
Pattern Recognit.
Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin, Alexander Binder, Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
2021 J jnl
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy.
CoRR
Christopher J. Anders, David Neumann, Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin
2020 — conf
ECQ
xxAI@ICML
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
2020 B conf
Explanation-Guided Training for Cross-Domain Few-Shot Classification.
ICPR
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, Alexander Binder
2020 J jnl
Explanation-Guided Training for Cross-Domain Few-Shot Classification.
CoRR
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, Alexander Binder
2020 J jnl
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond.
CoRR
Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin, Christopher J. Anders, Klaus-Robert Müller
2020 B conf
Towards Best Practice in Explaining Neural Network Decisions with LRP.
IJCNN
Maximilian Kohlbrenner, Alexander Bauer, Shinichi Nakajima, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin
2020 J jnl
Understanding Image Captioning Models beyond Visualizing Attention.
CoRR
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Alexander Binder
2020 B conf
Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution.
ICPR
Gary S. W. Goh, Sebastian Lapuschkin, Leander Weber, Wojciech Samek, Alexander Binder
2020 J jnl
Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution.
CoRR
Gary S. W. Goh, Sebastian Lapuschkin, Leander Weber, Wojciech Samek, Alexander Binder
2019 J jnl
Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet un-Hans'ed.
CoRR
Christopher J. Anders, Talmaj Marinc, David Neumann, Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin
2019 — ch.
Layer-Wise Relevance Propagation: An Overview.
Explainable AI
Grégoire Montavon, Alexander Binder, Sebastian Lapuschkin, Wojciech Samek, Klaus-Robert Müller
2019 J jnl
On the Understanding and Interpretation of Machine Learning Predictions in Clinical Gait Analysis Using Explainable Artificial Intelligence.
CoRR
Fabian Horst, Djordje Slijepcevic, Sebastian Lapuschkin, Anna-Maria Raberger, Matthias Zeppelzauer, Wojciech Samek, Christian Breiteneder, Wolfgang Immanuel Schöllhorn, Brian Horsak
2019 — —
Opening the machine learning black box with Layer-wise Relevance Propagation.
Sebastian Lapuschkin
2019 J jnl
Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning.
CoRR
Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin, Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
2019 J jnl
Resolving challenges in deep learning-based analyses of histopathological images using explanation methods.
CoRR
Miriam Hägele, Philipp Seegerer, Sebastian Lapuschkin, Michael Bockmayr, Wojciech Samek, Frederick Klauschen, Klaus-Robert Müller, Alexander Binder
2019 J jnl
Towards best practice in explaining neural network decisions with LRP.
CoRR
Maximilian Kohlbrenner, Alexander Bauer, Shinichi Nakajima, Alexander Binder, Wojciech Samek, Sebastian Lapuschkin
2019 J jnl
Unmasking Clever Hans Predictors and Assessing What Machines Really Learn.
CoRR
Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller
2019 J jnl
iNNvestigate Neural Networks!
J. Mach. Learn. Res.
Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele, Kristof T. Schütt, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller, Sven Dähne, Pieter-Jan Kindermans
2018 J jnl
Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals.
CoRR
Sören Becker, Marcel Ackermann, Sebastian Lapuschkin, Klaus-Robert Müller, Wojciech Samek
2018 J jnl
What is Unique in Individual Gait Patterns? Understanding and Interpreting Deep Learning in Gait Analysis.
CoRR
Fabian Horst, Sebastian Lapuschkin, Wojciech Samek, Klaus-Robert Müller, Wolfgang Immanuel Schöllhorn
2018 J jnl
iNNvestigate neural networks!
CoRR
Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer, Miriam Hägele, Kristof T. Schütt, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller, Sven Dähne, Pieter-Jan Kindermans
2017 J jnl
Evaluating the Visualization of What a Deep Neural Network Has Learned.
IEEE Trans. Neural Networks Learn. Syst.
Wojciech Samek, Alexander Binder, Grégoire Montavon, Sebastian Lapuschkin, Klaus-Robert Müller
2017 J jnl
Explaining nonlinear classification decisions with deep Taylor decomposition.
Pattern Recognit.
Grégoire Montavon, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek, Klaus-Robert Müller
2017 Misc conf
Interpretable human action recognition in compressed domain.
ICASSP
Vignesh Srinivasan, Sebastian Lapuschkin, Cornelius Hellge, Klaus-Robert Müller, Wojciech Samek
2017 — conf
Understanding and Comparing Deep Neural Networks for Age and Gender Classification.
ICCV Workshops
Wojciech Samek, Alexander Binder, Sebastian Lapuschkin, Klaus-Robert Müller
2017 J jnl
Understanding and Comparing Deep Neural Networks for Age and Gender Classification.
CoRR
Sebastian Lapuschkin, Alexander Binder, Klaus-Robert Müller, Wojciech Samek
2016 A* conf
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks.
CVPR
Sebastian Lapuschkin, Alexander Binder, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
2016 J jnl
Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation.
CoRR
Wojciech Samek, Grégoire Montavon, Alexander Binder, Sebastian Lapuschkin, Klaus-Robert Müller
2016 — conf
Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers.
ICANN (2)
Alexander Binder, Grégoire Montavon, Sebastian Lapuschkin, Klaus-Robert Müller, Wojciech Samek
2016 J jnl
The LRP Toolbox for Artificial Neural Networks.
J. Mach. Learn. Res.
Sebastian Lapuschkin, Alexander Binder, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek