Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Clausthal University of TechnologyPhD CandidateFeb. 2025 - present -
University of MannheimPhD CandidateSept. 2023 - Jan. 2025 -
University of MannheimM.Sc. in Information ScienceJan. 2021 - Aug. 2023
-
Lappeenranta University of Technology, FinlandSemester AbroadJan. 2020 - Apr. 2020 -
University of MannheimB.Sc. in Information ScienceSep. 2017 - Dec. 2020
Experience
-
Ramblr GmbH, MunichPhD InternshipSept. 2025 - Nov. 2025 -
Robert-Bosch GmbH, BühlMasterandOct. 2022 - Apr. 2023 -
Robert-Bosch GmbH, BühlWorking StudentJul. 2022 - Aug. 2023
-
Institute for Enterprise Systems, MannheimScientific AssistantJan. 2022 - Aug. 2023 -
Grosse-Hornke, MünsterWorking StudentNov. 2021 - Jul. 2022 -
Robert-Bosch GmbH, BühlWorking StudentJan. 2021 - Dec. 2021
-
Robert-Bosch GmbH, BühlBachelorandSep. 2020 - Dec. 2020
-
Robert-Bosch GmbH, BühlInternMay 2020 - Aug. 2020
-
Porsche AG, WeissachWorking StudentOct. 2019 - Dec. 2019 -
Robert-Bosch GmbH, BühlInternJul. 2019 - Aug. 2019
Honors & Awards
-
Ideenwettbewerb Regionalpreis Mainz2025
News
Selected Publications (view all )
Concepts in Motion: Temporal Bottlenecks for Interpretable Video Classification
Patrick Knab, Sascha Marton, Philipp J Schubert, Drago Guggiana, Christian Bartelt
Preprint 2025
Conceptual models such as Concept Bottleneck Models (CBMs) have driven substantial progress in improving interpretability for image classification by leveraging human-interpretable concepts. However, extending these models from static images to sequences of images, such as video data, introduces a significant challenge due to the temporal dependencies inherent in videos, which are essential for capturing actions and events. In this work, we introduce MoTIF (Moving Temporal Interpretable Framework), an architectural design inspired by a transformer that adapts the concept bottleneck framework for video classification and handles sequences of arbitrary length. Within the video domain, concepts refer to semantic entities such as objects, attributes, or higher-level components (e.g., 'bow', 'mount', 'shoot') that reoccur across time - forming motifs collectively describing and explaining actions. Our design explicitly enables three complementary perspectives: global concept importance across the entire video, local concept relevance within specific windows, and temporal dependencies of a concept over time. Our results demonstrate that the concept-based modeling paradigm can be effectively transferred to video data, enabling a better understanding of concept contributions in temporal contexts while maintaining competitive performance. Code available at github.com/patrick-knab/MoTIF.
Concepts in Motion: Temporal Bottlenecks for Interpretable Video Classification
Patrick Knab, Sascha Marton, Philipp J Schubert, Drago Guggiana, Christian Bartelt
Preprint 2025
Conceptual models such as Concept Bottleneck Models (CBMs) have driven substantial progress in improving interpretability for image classification by leveraging human-interpretable concepts. However, extending these models from static images to sequences of images, such as video data, introduces a significant challenge due to the temporal dependencies inherent in videos, which are essential for capturing actions and events. In this work, we introduce MoTIF (Moving Temporal Interpretable Framework), an architectural design inspired by a transformer that adapts the concept bottleneck framework for video classification and handles sequences of arbitrary length. Within the video domain, concepts refer to semantic entities such as objects, attributes, or higher-level components (e.g., 'bow', 'mount', 'shoot') that reoccur across time - forming motifs collectively describing and explaining actions. Our design explicitly enables three complementary perspectives: global concept importance across the entire video, local concept relevance within specific windows, and temporal dependencies of a concept over time. Our results demonstrate that the concept-based modeling paradigm can be effectively transferred to video data, enabling a better understanding of concept contributions in temporal contexts while maintaining competitive performance. Code available at github.com/patrick-knab/MoTIF.
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
Patrick Knab, Sascha Marton, Christian Bartelt
28th European Conference on Artificial Intelligence (ECAI) 2025
LIME (Local Interpretable Model-agnostic Explanations) is a popular XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes image segmentation methods to identify fixed regions for calculating feature importance scores as explanations. Therefore, poor segmentation can weaken the explanation and reduce the importance of segments, ultimately affecting the overall clarity of interpretation. To address these challenges, we introduce the DSEG-LIME (Data-Driven Segmentation LIME) framework, featuring: i) a data-driven segmentation for human-recognized feature generation by foundation model integration, and ii) a user-steered granularity in the hierarchical segmentation procedure through composition. Our findings demonstrate that DSEG outperforms on several XAI metrics on pre-trained ImageNet models and improves the alignment of explanations with human-recognized concepts. The code is available under: https://github.com/patrick-knab/DSEG-LIME
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
Patrick Knab, Sascha Marton, Christian Bartelt
28th European Conference on Artificial Intelligence (ECAI) 2025
LIME (Local Interpretable Model-agnostic Explanations) is a popular XAI framework for unraveling decision-making processes in vision machine-learning models. The technique utilizes image segmentation methods to identify fixed regions for calculating feature importance scores as explanations. Therefore, poor segmentation can weaken the explanation and reduce the importance of segments, ultimately affecting the overall clarity of interpretation. To address these challenges, we introduce the DSEG-LIME (Data-Driven Segmentation LIME) framework, featuring: i) a data-driven segmentation for human-recognized feature generation by foundation model integration, and ii) a user-steered granularity in the hierarchical segmentation procedure through composition. Our findings demonstrate that DSEG outperforms on several XAI metrics on pre-trained ImageNet models and improves the alignment of explanations with human-recognized concepts. The code is available under: https://github.com/patrick-knab/DSEG-LIME
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse*, Patrick Knab*, Sascha Marton, Christian Bartelt, Margret Keuper (* equal contribution)
International Conference on Machine Learning (ICML) 2025
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Dataefficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. This removes reliance on textual descriptions and large-scale pre-training, making DCBMs applicable for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined ones, DCBMs enhance adaptability to new domains.
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse*, Patrick Knab*, Sascha Marton, Christian Bartelt, Margret Keuper (* equal contribution)
International Conference on Machine Learning (ICML) 2025
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Dataefficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. This removes reliance on textual descriptions and large-scale pre-training, making DCBMs applicable for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined ones, DCBMs enhance adaptability to new domains.
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse*, Patrick Knab*, Sascha Marton, Christian Bartelt, Margret Keuper (* equal contribution)
Conference on Computer Vision and Pattern Recognition (CVPR) @ XAI4CV Workshop 2025
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Dataefficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. This removes reliance on textual descriptions and large-scale pre-training, making DCBMs applicable for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined ones, DCBMs enhance adaptability to new domains.
DCBM: Data-Efficient Visual Concept Bottleneck Models
Katharina Prasse*, Patrick Knab*, Sascha Marton, Christian Bartelt, Margret Keuper (* equal contribution)
Conference on Computer Vision and Pattern Recognition (CVPR) @ XAI4CV Workshop 2025
Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive image corpora, limiting their effectiveness in data-sparse scenarios. We propose Dataefficient CBMs (DCBMs), which reduce the need for large sample sizes during concept generation while preserving interpretability. DCBMs define concepts as image regions detected by segmentation or detection foundation models, allowing each image to generate multiple concepts across different granularities. This removes reliance on textual descriptions and large-scale pre-training, making DCBMs applicable for fine-grained classification and out-of-distribution tasks. Attribution analysis using Grad-CAM demonstrates that DCBMs deliver visual concepts that can be localized in test images. By leveraging dataset-specific concepts instead of predefined ones, DCBMs enhance adaptability to new domains.