Maximilian Dreyer

From "Where" to "What": Towards Human-Understandable Explanations through Concept Relevance Propagation

S. Lapuschkin, W. Samek, S. Bosse, 2022, ArXiv.

Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations

S. Lapuschkin, W. Samek, Thomas Wiegand, 2022, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs pdf

Wojciech Samek, Sebastian Lapuschkin, Daniel Becking, 2020, xxAI@ICML.

Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models

S. Lapuschkin, W. Samek, Maximilian Dreyer, 2023, ArXiv.

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

S. Lapuschkin, W. Samek, Karsten Müller, 2021, xxAI@ICML.

From attribution maps to human-understandable explanations through Concept Relevance Propagation

S. Lapuschkin, S. Bosse, Maximilian Dreyer, 2023, Nature Machine Intelligence.

From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space

Christopher J. Anders, Maximilian Dreyer, Frederik Pahde, 2023, AAAI.

From Hope to Safety: Unlearning Biases of Deep Models by Enforcing the Right Reasons in Latent Space

Christopher J. Anders, W. Samek, Maximilian Dreyer, 2023, ArXiv.

AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers

Reduan Achtibat, Maximilian Dreyer, Wojciech Samek, 2024, ArXiv.

From attribution maps to human-understandable explanations through Concept Relevance Propagation

W. Samek, S. Bosse, Thomas Wiegand, 2022, Nature Machine Intelligence.