David Münch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David Münch has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Michael Arens
Fraunhofer IOSB
11 shared publications - Jens Bayer
Fraunhofer IOSB
7 shared publications - Stefan Becker
Fraunhofer IOSB
4 shared publications - Vanessa Buhrmester
Fraunhofer IOSB, Gutleuthausstrasse 1, 76275 Ettlingen, Germany
4 shared publications - Ann-Kristin Grosselfinger
Fraunhofer IOSB
2 shared publications - Jürgen Beyerer
Karlsruhe Institute of Technology
2 shared publications
Latest Publications
- 4 August 2026
- Published by Springer Nature
- p. 622-634
Higher-Order Adversarial Patches for Real-Time Object Detectors
- 4 August 2026
- Published by Springer Nature
- p. 622-634
Higher-Order Adversarial Patches for Real-Time Object Detectors
- Open Access
- 25 April 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (3) , 1-11
Traversing the subspace of adversarial patches
Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part of a low-dimensional manifold. To verify the thesis with adversarial patches–a special form of adversarial attack that can be used to fool object detectors in the physical world–this paper provides an analysis of a set of adversarial patches and investigates the reconstruction abilities of five different dimensionality reduction methods. Quantitatively, the performance of reconstructed patches in an attack setting is measured and the impact of sampled patches from the latent space during adversarial training is investigated. The evaluation is performed on two publicly available datasets for person detection. The results indicate that more sophisticated dimensionality reduction methods offer no advantages over a simple principal component analysis.
- 25 April 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (3) , 1-11
Open AccessTraversing the subspace of adversarial patches
Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part of a low-dimensional manifold. To verify the thesis with adversarial patches–a special form of adversarial attack that can be used to fool object detectors in the physical world–this paper provides an analysis of a set of adversarial patches and investigates the reconstruction abilities of five different dimensionality reduction methods. Quantitatively, the performance of reconstructed patches in an attack setting is measured and the impact of sampled patches from the latent space during adversarial training is investigated. The evaluation is performed on two publicly available datasets for person detection. The results indicate that more sophisticated dimensionality reduction methods offer no advantages over a simple principal component analysis.
- 3 December 2023
- Published by Springer Nature
- p. 274-284
Eigenpatches—Adversarial Patches from Principal Components
- 3 December 2023
- Published by Springer Nature
- p. 274-284
Eigenpatches—Adversarial Patches from Principal Components
- 20 August 2023
- Published by Springer Nature
- p. 51-56
Companion Paper: Deep Saliency Map Generators for Multispectral Video Classification
- 20 August 2023
- Published by Springer Nature
- p. 51-56
Companion Paper: Deep Saliency Map Generators for Multispectral Video Classification
- Open Access
Eigenpatches -- Adversarial Patches from Principal Components
Adversarial patches are still a simple yet powerful white box attack that can be used to fool object detectors by suppressing possible detections. The patches of these so-called evasion attacks are computational expensive to produce and require full access to the attacked detector. This paper addresses the problem of computational expensiveness by analyzing 375 generated patches, calculating the principal components of these and show, that linear combinations of the resulting "eigenpatches" can be used to fool object detections successfully.
Open AccessEigenpatches -- Adversarial Patches from Principal Components
Adversarial patches are still a simple yet powerful white box attack that can be used to fool object detectors by suppressing possible detections. The patches of these so-called evasion attacks are computational expensive to produce and require full access to the attacked detector. This paper addresses the problem of computational expensiveness by analyzing 375 generated patches, calculating the principal components of these and show, that linear combinations of the resulting "eigenpatches" can be used to fool object detections successfully.
- Top Cited PapersOpen Access
- 8 December 2021
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 3 (4) , 966-989
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
- 8 December 2021
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 3 (4) , 966-989
Top Cited PapersOpen AccessAnalysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
- 21 February 2021
- Published by Springer Nature
- p. 26-40
Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition
- 21 February 2021
- Published by Springer Nature
- p. 26-40
Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition
- Open Access
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition
Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. The contribution of this work is (i) the examination of the portability of recent image-based OoD-detectors for graph-based input data, (ii) a Metric Learning-based approach to detect OoD-samples, and (iii) the introduction of a novel semi-synthetic action recognition dataset. The evaluation shows that image-based OoD-methods can be applied to graph-based data. Additionally, there is a gap between the performance on intraclass and intradataset results. First methods as the examined baseline or ODIN provide reasonable results. More sophisticated network architectures - in contrast to their image-based application - were surpassed in the intradataset comparison and even lead to less classification accuracy.
Open AccessImage-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition
Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. The contribution of this work is (i) the examination of the portability of recent image-based OoD-detectors for graph-based input data, (ii) a Metric Learning-based approach to detect OoD-samples, and (iii) the introduction of a novel semi-synthetic action recognition dataset. The evaluation shows that image-based OoD-methods can be applied to graph-based data. Additionally, there is a gap between the performance on intraclass and intradataset results. First methods as the examined baseline or ODIN provide reasonable results. More sophisticated network architectures - in contrast to their image-based application - were surpassed in the intradataset comparison and even lead to less classification accuracy.
- Open Access
Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
Open AccessAnalysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
- 23 November 2019
- Published by Springer Nature
- p. 245-258
Data Anonymization for Data Protection on Publicly Recorded Data
- 23 November 2019
- Published by Springer Nature
- p. 245-258
Data Anonymization for Data Protection on Publicly Recorded Data