Підписатись
Maximilian Dreyer
Maximilian Dreyer
Підтверджена електронна адреса в hhi.fraunhofer.de
Назва
Посилання
Посилання
Рік
From attribution maps to human-understandable explanations through Concept Relevance Propagation
R Achtibat, M Dreyer, I Eisenbraun, S Bosse, T Wiegand, W Samek, ...
Nature Machine Intelligence 5 (9), 1006-1019, 2023
1662023
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
M Dreyer, R Achtibat, T Wiegand, W Samek, S Lapuschkin
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023
262023
AttnLRP: Attention-aware Layer-wise Relevance Propagation for Transformers
R Achtibat, SMV Hatefi, M Dreyer, A Jain, T Wiegand, S Lapuschkin, ...
Forty-first International Conference on Machine Learning (ICML 2024), 2024
232024
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models
F Pahde, M Dreyer, W Samek, S Lapuschkin
Medical Image Computing and Computer Assisted Intervention - MICCAI 2023 …, 2023
192023
ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
D Becking, M Dreyer, W Samek, K Müller, S Lapuschkin
International Workshop on Extending Explainable AI Beyond Deep Models and …, 2022
172022
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
M Dreyer, R Achtibat, W Samek, S Lapuschkin
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
112024
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
M Dreyer, F Pahde, CJ Anders, W Samek, S Lapuschkin
Proceedings of the AAAI Conference on Artificial Intelligence 38 (19), 21046 …, 2024
102024
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
F Pahde, M Dreyer, M Weckbecker, L Weber, CJ Anders, T Wiegand, ...
ICLR 2025, 0
5*
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
M Dreyer, E Purelku, J Vielhaben, W Samek, S Lapuschkin
CVPR 2024 Workshop Proceedings (XAI4CV Spotlight), 2024
42024
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
SMV Hatefi, M Dreyer, R Achtibat, T Wiegand, W Samek, S Lapuschkin
Forty-first International Conference on Machine Learning Workshops (eXCV …, 2024
22024
Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
C Tinauer, A Damulina, M Sackl, M Soellradl, R Achtibat, M Dreyer, ...
World Conference on Explainable Artificial Intelligence, 202-216, 2024
12024
Mechanistic understanding and validation of large AI models with SemanticLens
M Dreyer, J Berend, T Labarta, J Vielhaben, T Wiegand, S Lapuschkin, ...
arXiv preprint arXiv:2501.05398, 2025
2025
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
D Bareeva, M Dreyer, F Pahde, W Samek, S Lapuschkin
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
2024
У даний момент система не може виконати операцію. Спробуйте пізніше.
Статті 1–13