Maximilian Dreyer

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 15

Top Topics

Quantization Noise

Bias Correction

Top Venues

Nat. Mac. Intell.

Publications

Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space. AAAI (2024)
Dilyara Bareeva, Maximilian Dreyer, Frederik Pahde, Wojciech Samek, Sebastian Lapuschkin
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression. CoRR (2024)
Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Aakriti Jain, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek
AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers. CoRR (2024)
Maximilian Dreyer, Erblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits. CoRR (2024)
Christian Tinauer, Anna Damulina, Maximilian Sackl, Martin Soellradl, Reduan Achtibat, Maximilian Dreyer, Frederik Pahde, Sebastian Lapuschkin, Reinhold Schmidt, Stefan Ropele, Wojciech Samek, Christian Langkammer
Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification. CoRR (2024)
Maximilian Dreyer, Frederik Pahde, Christopher J. Anders, Wojciech Samek, Sebastian Lapuschkin
From Hope to Safety: Unlearning Biases of Deep Models by Enforcing the Right Reasons in Latent Space. CoRR (2023)
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
From attribution maps to human-understandable explanations through Concept Relevance Propagation. Nat. Mac. Intell. 5 (9) (2023)
Maximilian Dreyer, Reduan Achtibat, Wojciech Samek, Sebastian Lapuschkin
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations. CoRR (2023)
Frederik Pahde, Maximilian Dreyer, Wojciech Samek, Sebastian Lapuschkin
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. CoRR (2023)
Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations. CVPR Workshops (2023)
Frederik Pahde, Maximilian Dreyer, Wojciech Samek, Sebastian Lapuschkin
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models. MICCAI (2) (2023)
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
From "Where" to "What": Towards Human-Understandable Explanations through Concept Relevance Propagation. CoRR (2022)
Maximilian Dreyer, Reduan Achtibat, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations. CoRR (2022)
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
: Explainability-Driven Quantization for Low-Bit and Sparse DNNs. CoRR (2021)
Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
: Explainability-Driven Quantization for Low-Bit and Sparse DNNs. xxAI@ICML (2020)