Veröffentlichungen

Nachstehend sind wissenschaftliche Beiträge und Veröffentlichungen aus dem Projekt KI Absicherung aufgeführt:

1. Matthias Rottmann, Robin Chan, Peter Schlicht, Fabian Hüger: Detection of False Positive and False Negative Samples in Semantic Segmentation. In: DATE2020, Proceedings DATE 2020, Grenoble, 9.-13.03.2020
2. Marco Hoffman, Dr. Alexander Pohl, Patrick Prill, Dr. Michael Mlynarski: Die Gefahren lauern vor allem hinter den Ecken – Corner Cases und ihre Tücken. In: German Testing Magazin, April 2020
3. Timo Sämann, Peter Schlicht, Fabian Hüger: Strategy to Increase the Safety of a DNN-based Perception for HAD Systems. In: arXiv preprint 20.02.2020
4. Andreas Bär, Marvin Klingner, Serin Varghese, Fabian Hüger, Peter Schlicht, Tim Fingscheidt: Robust Semantic Segmentation by Redundant Networks With a Layer-Specific Loss Contribution and Majority Vote. In: Proc. of CVPR - Workshop on Safe Artificial Intelligence for Automated Driving (CVPR SAIAD 2020), Seattle, WA, USA, Juni 2020
5. Christoph Gladisch, Christian Heinzemann, Martin Herrmann, Matthias Woehrle: Leveraging combinatorial testing for safety-critical computer vision datasets. In: Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD) 2020, Seattle (USA), 14.06.2020
6. Oliver Grau, Korbinian Hagn, Qutub Syed Sha: Computational validation of perceptional functions. In: Safe AI for automated Driving – IEEE Computer Society Conference on  Computer Vision and Pattern Recognition (CVPR), Proceedings of Computer Vision and Pattern Recognition – Workshop, Seattle (USA), 14. – 19.06.2020
7. Fabian Küppers, Jan Kronenberger, Amirhossein Shantia, Anselm Haselhoff: Multivariate Confidence Calibration for Object Detection. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle (USA), 16. – 18.06.2020
8. Jonas Löhdefink, Justin Fehrling, Marvin Klingner, Fabian Hüger, Peter Schlicht, Nico M. Schmidt, Tim Fingscheidt: Self-Supervised Domain Mismatch Estimation for Autonomous Perception. In: Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD) 2020, Seattle (USA), 14.06.2020
9. Serin Varghese, Yasin Bayzidi, Andreas Bär, Nikhil Kapoor, Sounak Lahiri, Jan David Schneider, Nico Schmidt, Peter Schlicht, Fabian Hüger, Tim Fingscheidt: Unsupervised Temporal Consistency Metric for Video Segmentation in Highly-Automated Driving. In: Proc. of CVPR - Workshop on Safe Artificial Intelligence for Automated Driving (CVPR SAIAD 2020), Seattle, WA, USA, Juni 2020
10. Joachim Sicking, Maram Akila, Tim Wirtz, Sebastian Houben, Asja Fischer: Characteristics of Monte Carlo Dropout in Wide Neural Networks. In Workshop on Uncertainty & Robustness in Deep Learning (at ICML); Wien (Österreich), 17.07.2020
11. Michael Fürst, Emil Schreiber: KIA – Annotations Format (V2.1) Design Process and Decisions. In: OpenLABEL Project Meeting, online, 23. – 24.07.2020
12. Stephanie Abrecht, Lydia Gauerhof, Christoph Gladisch, Konrad Groh, Christian Heinzemann, Matthias Woehrle: Testing Deep Learning-based Visual Perception for Automated Driving. In: Journal ACM Transactions on Cyber-Physical Systems, Speical Issue on Artificial Intelligence and Cyber-Physical Systems
13. Michael Fürst, Oliver Wasenmüller, Didier Stricker: LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB. In IEEE International Conference on Intelligent Transportation Systems, Rhodes (Griechenland), 20. – 23.09.2020
14. Juncong Fei, Wenbo Chen, Philipp Heidenreich, Sascha Wirges, Christoph Stiller: Semantic Voxels: Sequential Fusion for 3D PedestrianDetection using LiDAR Point Cloud and Semantic Segmentation. In: IEEE International Conference on Multisensor Fusion and Integration, Karlsruhe (Deutschland), 14. – 16.09.2020
15. Oliver Willers, Sebastian Sudholt, Shervin Raafatnia, Stephanie Abrecht: Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks. In: SAFECOMP 2020, Lecture Notes on Computer Science Lissabon (Portugal), 15. – 18.09.2020
16. Stephanie Abrecht, Maram Akila, Sujan Sai Gannamaneni, Konrad Groh, Christian Heinzemann, Sebastian Houben, Matthias Woehrle: Revisiting Neuron Coverage and its Application to Test Generation. In: Third International Workshop on Artificial Intelligence Safety Engineering, Computer Safety, Reliability and Security: SAFECOMP 2020 Worshops, Lissabon (Portugal), 15.09.2020
17. Gesina Schwalbe, Bernhard Knie, Timo Sämann, Timo Dobberphul, Lydia Gauerhof, Shervin Raaftnia, Oliver Willers: Structuring the Safety Argumentation for Deep Neural Networks. In: SafeComp 2020, Computer Safety, Reliability and Security, Lissabon (Portugal), 15. – 18.09.2020
18. Michael Weber, Christof Wendenius, J. Marius Zöllner: Runtime Optimization of a CNN for Environment Perception. In: IEEE Intelligent Vehicles Symposium (IV) 2020, Proceedings of  the IEEE Intelligent Vehicles Symposium, Las Vegas (USA), 21.-23.10.2020
19. Peter Nöst, Korbinian Hagn, Oliver Grau: Characterizing Data Sets for training and validation in automated driving. In: 4. ACM Computer Science in Cars Symposium (CSCS 2020), Ingolstadt (online), 02.12.2020
20. Korbinian Hagn, Oliver Grau: Increasing realism of synthetic datasets through additive sensor and lens artefacts. In: 4. ACM Computer Science in Cars Symposium (CSCS 2020), Ingolstadt (online), 02.12.2020
21. Nikhil Kapoor, Chun Yuan, Serin Varghese, Jonas Löhdefink, Roland Zimmermann, Serin Varghese, Fabian Hüger, Nico Schmidt, Peter Schlicht, Tim Fingscheidt: A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations to Efficiently Improve the Robustness of CNNs. In: 4. ACM Computer Science in Cars Symposium (CSCS 2020), Ingolstadt (online), 02.12.2020
22. Qutub Syed Sha, Oliver Grau, Korbinian Hagn: DNN Analysis through Synthetic Data Variation. In: 4. ACM Computer Science in Cars Symposium (CSCS 2020), Ingolstadt (online), 02.12.2020
23. Michael Fürst, Shriya T.P. Gupta, René Schuster, Oliver Wasenmüller, Didier Stricker: HPERL: 3D Human Pose Estimation from RGB and LiDAR. In: 25th IEEE International Conference on Pattern Recognition, Milan, Italy (online), 10.-13.01.2021
24. Timo Sämann, Horst-Michael Gross: Online Out-of-Domain Detection for Automated Driving. In: Machine Learning in Certified Systems Workshop (https://mlcertifiedsystems.deel.ai/), 14.-15.01.2021
25. Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan Kronenberger, Fabian Küppers, Jonas Löhdefink, Michael Mlynarski, Michael Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander Pohl, Varun Ravi-Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan Rüping, Timo Sämann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian Wirkert, Tim Wirtz, and Matthias Woehrle: Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety. KI Absicherung 2020
26. Michael Mock, Stephan Scholz, Loren Schwarz,  Thomas Stauner, Fabian Hüger, Frédérik Blank, Andreas Rohatschek, KI-Absicherung: Proof of Project Concept conducted, 01.04.2021
27. Andreas Blattmann, Timo Milbich, Michael Dorkenwald, Björn Ommer, Heidelberg Collaboratory for Image Processing: Behavior-Driven Synthesis of Human Dynamics, In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
28. Andreas Blattmann, Timo Milbich, Michael Dorkenwald, Björn Ommer, Interdisciplinary Center for Scientific Computing: Understanding Object Dynamics for Interactive Image-to-Video Synthesis, In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
29. Anselm Haselhoff , Jan Kronenberger, Fabian Kuppers, Jonas Schneider: Towards Black-Box Explainability with Gaussian Discriminant Knowledge Distillation, In: SAIAD Workshop at IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
30. Patrick Feifel, Frank Bonarens, Frank Koster, Stellantis: Reevaluating the Safety Impact of Inherent Interpretability on Deep Neural Networks for Pedestrian Detection, In: SAIAD Workshop at IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
31. Julia Rosenzweig , Joachim Sicking, Sebastian Houben, Michael Mock, Maram Akila: Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities, In: SAIAD Workshop at IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
32. Serin Varghese, Sharat Gujamagadi, Marvin Klingner, Nikhil Kapoor, Andreas Bar, Jan David Schneider, Kira Maag, Peter Schlicht, Fabian Huger, Tim Fingscheidt, Volkswagen Group Automation, University of Wuppertal: An Unsupervised Temporal Consistency (TC) Loss to Improve the Performance of Semantic Segmentation Networks, In: SAIAD Workshop at IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (Home | CVPR 2021 (thecvf.com), 19-25.06.2021
33. Joachim Sicking, Maram Akila: Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties.ICLR 2021, In: Ninth International Conference on Learning Representations, virtual, 04.052021  
34. Dominik Brüggemann, Hanno Gottschalk, Christian Hellert, Fabian Hüger, Michael Mock, Shervin Raafatnia, Gesina Schwalbe,  DNN-specific Safety Concerns. In: KI Familie Newsletter, Ausgabe Juli 2021
35. Gesina Schwalbe: Verification of Size Invariance in DNN Activations using Concept Embeddings. In: 17th International Conference on Artificial Intelligence Applications and Innovations (AIAI 2021), Kreta (online), 25-27.06.2021
36. Simon Burton, Mario Trapp: Effectiveness of Object Detection Calibration andAnomaly Detection Integration with respect to Safety-Related Metrics. In: International Conference on Dependable System and Networks, Taipei, 21-24.06.2021
37. Hanno Stage, Lennart Ries, Jacob Langner, Philipp Rigoll, Eric Sax: Exploration of Latent Spaces for Function Agnostic Domain Shift in Automated Driving. In: Safe Artificial Intelligence for Automated Driving, Online, 19.06.2021 
38. Fabian Hüger, Jan David Schneider, Nikhil Kapoor, Andreas Bär: An Unsupervised Temporal Consistency (TC) Loss to Improve the Performance of Semantic Segmentation Networks. In: Safe AI for Automated Driving –   IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), virtual, 19.-25-06.2021
39. Lennart Ries: Exploration of Latent Spaces for Function Agnostic Domain Shift in Automated Driving. In: Safe Artificial Intelligence for Automated Driving, virtual, 19.06.2021 
40. Dominik Brüggemann, Robin Chan, Hanno Gottschalk, Stefan Bracke: Software architecture for human-centered reliability assessment for neural networks in autonomous driving. In: 11th IMA International Conference on Modelling in Industrial Maintenance and Reliability (MIMAR), virtual, 29.06.-01.07.2021 
41. Juncong Fei, Philipp Heidenreich: PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data. In: IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan, virtual, 11.07-15.07.2021
42. Anselm Haselhoff, Jan Kronenberger, Fabian Küppers, Jonas Schneider, Bayesian Confidence Calibration for Epistemic Uncertainty Modelling. In:  IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan, virtual, 11.07-15.07.2021
43. Nikhil Kapoor, Fabian Hüger, Serin Varghese, Andreas Bär, David Schneider: From a Fourier-Domain Perspective on Adversarial Examples to a Wiener Filter Defense for Semantic Segmentation. In: International Joint Conference on Neural Networks(IJCNN) 2021, virtual, 18.07-22.07.2021
44. Michael Mock, Stephan Scholz, Fréderik Blank, Fabian Hüger, Andreas Rohatschek, Loren Schwarz, Thomas Stauner: An Integrated Approach to a Safety Argumentation for AI-Based Perception Functions in Automated Driving. In: Computer Safety, Reliability, and Security. SAFECOMP 2021 Workshops, hybrid, 7.09.2021
45. Deepthi Sreenivasaiah, Johannes Otterbach, Thomas Wollmann: MEAL: Manifold Embedding-based Active Learning. In: ICCV 2021 - Workshop on "Embedded and Real-World Computer Vision in Autonomous Driving” 2021, 11.10.2021
46. Lukas Stäcker, Juncong Fei, Philipp Heidenreich, Frank Bonarens, Jason Rambach, Didier Stricker, Christoph Stiller: Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimization. In: International Conference on Computer Vision, (ICCV), 11.10.2021
47. Andreas Blattmann,Timo Milbich, Michael Dorkenwald, Bjorn Ommer: iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis. In: International Conference on Computer Vision, (ICCV), 11.10.2021
48. Robin Chan, Matthias Rottmann, Hanno Gottschalk: Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation. In: International Conference on Computer Vision, (ICCV), 11.10.2021
49. Sujan Gannamaneni, Sebastian Houben, Maram Akila: Semantic Concept Testing in Autonomous Driving by Extraction of Object-Level Annotations from CARLA. In: ICCV 2021 - Workshop on "Embedded and Real-World Computer Vision in Autonomous Driving” 2021, 11.10.2021
50. Johannes Bernhard, Thomas Schulik, Mark Schutera, Erik Sax, Adaptive test case selection for DNN-based perception functions. In: IEEE International Symposium on Systems Engineering (ISSE), 13-15.09.2021, Vienna
51. Mert Keser, Artem Savkin, Federico Tombari, Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 27.9-1.10.2021, Prague
52. Mert Keser, Artem Savkin, Federico Tombari, Content Disentanglement for Semantically Consistent Synthetic-to-Real Domain Adaptation. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 27.9-1.10.2021, Prague
53. Tianming Qiu, Laplace Approximation with Diagonalized Hessian for Over-parameterized Neural Networks. In: NeurIPS 2021 Bayesian Deep Learing workshop, 14.12.2021. virtual
54. Lydia Gauerhof, On the Necessity of Explicit Artifact Links in Safety Assurance Cases for Machine Learning. In: IEEE International Conference on Software Reliability Engineering Workshops, 25-28.10.2021, China
55. Gesina Schwalbe, Concept Embedding Analysis: A Review. In: Springer Journal Artificial Intelligence Review, 25.03.2022
56. Tim Fingscheidt, Hanno Gottschalk and Sebastian Houben, Deep Neural Networks and Data for Automated Driving.
57. Ahmed Hammam, Seyed Ghobadi,  Frank Bonarens, Christoph Stiller, Real-time Uncertainty Estimation Based On Intermediate Layer Variational Inference. In: ACM CSCS 2021, Ingolstadt.
58. Oliver Grau, Korbinian Hagn, High-fidelity procedural data synthesis for validation and training of perception functions.  In: CVMP 2021, London, 06.12.2022.
59. Tobias Riedlinger, Matthias Rottmann, Marius Schubert, Hanno Gottschalk, Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors. In: CVPR 2022 New Orleans, 19.06.2022.
60. Alexander Lehner, Stefano Gasperini, Alvaro Marcos-Ramiro, Michael Schmidt, Mohammad-Ali Nikouei Mahani, Benjamin Busam, Nassir Navab, Federico Tombari, 3D-VField: Learning to Adversarially Deform Point Clouds for Robust 3D Object Detection. In: CVPR 2022 New Orleans, 19.06.2022.
61. Robin Rombach , Andreas Blattmann, Patrick Esser, Dominik Lorenz, Bjoern Ommer: High-Resolution Image Synthesis with Latent Diffusion Models. In: CVPR 2022 New Orleans, 19.06.2022.
62. Andreas Bär, Marvin Klingner, Jonas Löhdefink, Fabian Hüger, Peter Schlicht, Tim Fingscheidt: Performance Prediction for Semantic Segmentation by a Self-Supervised Image Reconstruction Decoder. In: CVPR 2022 New Orleans, 19.06.2022.
63. Svetlana Pavlitskaya, Şiyar Yıkmış, J. Marius Zöllner: Is Neuron Coverage Needed to Make Person Detection More Robust? In: CVPR 2022 New Orleans, 19.06.2022.
64. Elena Haedecke, Michael Mock, Maram Akila, ScrutinAI: A Visual Analytics Approach for the Semantic Analysis of Deep Neural Network Predictions. In: EuroVA 2022, 13th international EuroVis workshop on Visual Analytics, Rome, Italy, 13.06.2022.
65. Robin Chan, Radin Dardashti, Meike Osinski, Matthias Rottmann, Dominik Brüggemann, Cilia Rücker, Peter Schlicht, Fabian Hüger, Nikol Rummel, Hanno Gottschalk: What should AI see? Using the Public's Opinion to Determine the Perception of an AI. 09.06.2022.
66. Patrick Feifel, Benedikt Franke, Arne Raulf, Friedhelm Schwenker, Frank Bonarens, Frank Köster: Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection. In: AISafety Workshop, IJCAI-ECAI, 24.07.2022.
67. Svetlana Pavlitskaya, Bianca-Marina Codău and J. Marius Zöllner: Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection. In: AISafety Workshop, IJCAI-ECAI, 24.07.2022.