From attribution maps to human-understandable explanations through Concept Relevance Propagation
Achtibat, Reduan, Dreyer, Maximilian, Eisenbraun, Ilona, Bosse, Sebastian, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Published in Nature machine intelligence (01.09.2023)
Published in Nature machine intelligence (01.09.2023)
Get full text
Journal Article
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
Bareeva, Dilyara, Dreyer, Maximilian, Pahde, Frederik, Samek, Wojciech, Lapuschkin, Sebastian
Published in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (17.06.2024)
Published in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (17.06.2024)
Get full text
Conference Proceeding
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
Dreyer, Maximilian, Achtibat, Reduan, Samek, Wojciech, Lapuschkin, Sebastian
Published in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (17.06.2024)
Published in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (17.06.2024)
Get full text
Conference Proceeding
Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
Bareeva, Dilyara, Dreyer, Maximilian, Pahde, Frederik, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 15.04.2024
Year of Publication 15.04.2024
Get full text
Journal Article
PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
Dreyer, Maximilian, Purelku, Erblina, Vielhaben, Johanna, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 09.04.2024
Year of Publication 09.04.2024
Get full text
Journal Article
Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
Dreyer, Maximilian, Achtibat, Reduan, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 28.11.2023
Year of Publication 28.11.2023
Get full text
Journal Article
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
Dreyer, Maximilian, Achtibat, Reduan, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01.06.2023)
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01.06.2023)
Get full text
Conference Proceeding
Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models
Pahde, Frederik, Dreyer, Maximilian, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 22.03.2023
Year of Publication 22.03.2023
Get full text
Journal Article
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Hatefi, Sayed Mohammad Vakilzadeh, Dreyer, Maximilian, Achtibat, Reduan, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 22.08.2024
Year of Publication 22.08.2024
Get full text
Journal Article
Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations
Dreyer, Maximilian, Achtibat, Reduan, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 21.11.2022
Year of Publication 21.11.2022
Get full text
Journal Article
AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
Achtibat, Reduan, Hatefi, Sayed Mohammad Vakilzadeh, Dreyer, Maximilian, Jain, Aakriti, Wiegand, Thomas, Lapuschkin, Sebastian, Samek, Wojciech
Year of Publication 08.02.2024
Year of Publication 08.02.2024
Get full text
Journal Article
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
Dreyer, Maximilian, Pahde, Frederik, Anders, Christopher J, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 18.08.2023
Year of Publication 18.08.2023
Get full text
Journal Article
ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
Becking, Daniel, Dreyer, Maximilian, Samek, Wojciech, Müller, Karsten, Lapuschkin, Sebastian
Year of Publication 09.09.2021
Year of Publication 09.09.2021
Get full text
Journal Article
Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
Tinauer, Christian, Damulina, Anna, Sackl, Maximilian, Soellradl, Martin, Achtibat, Reduan, Dreyer, Maximilian, Pahde, Frederik, Lapuschkin, Sebastian, Schmidt, Reinhold, Ropele, Stefan, Samek, Wojciech, Langkammer, Christian
Year of Publication 16.04.2024
Year of Publication 16.04.2024
Get full text
Journal Article
From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Achtibat, Reduan, Dreyer, Maximilian, Eisenbraun, Ilona, Bosse, Sebastian, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 07.06.2022
Year of Publication 07.06.2022
Get full text
Journal Article
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
Pahde, Frederik, Dreyer, Maximilian, Weber, Leander, Weckbecker, Moritz, Anders, Christopher J, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Year of Publication 07.02.2022
Year of Publication 07.02.2022
Get full text
Journal Article