TY - INPR A1 - Müller, Patrick A1 - Braun, Alexander A1 - Keuper, Margret T1 - Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models N2 - Deep neural networks (DNNs) have proven to be successful in various computer vision applications such that models even infer in safety-critical situations. Therefore, vision models have to behave in a robust way to disturbances such as noise or blur. While seminal benchmarks exist to evaluate model robustness to diverse corruptions, blur is often approximated in an overly simplistic way to model defocus, while ignoring the different blur kernel shapes that result from optical systems. To study model robustness against realistic optical blur effects, this paper proposes two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions. OpticsBench examines primary aberrations such as coma, defocus, and astigmatism, i.e. aberrations that can be represented by varying a single parameter of Zernike polynomials. To go beyond the principled but synthetic setting of primary aberrations, LensCorruptions samples linear combinations in the vector space spanned by Zernike polynomials, corresponding to 100 real lenses. Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly, indicating the need to consider realistic image corruptions to evaluate a model's robustness against blur. KW - Maschinelles Lernen KW - Maschinelles Sehen KW - Tiefes neuronales Netz KW - Objekterkennung KW - Abbildungsfehler Y1 - 2025 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-55457 PB - arXiv ET - v1 ER - TY - INPR A1 - Wolf, Dominik Werner A1 - Balaji, Prasannavenkatesh A1 - Braun, Alexander A1 - Ulrich, Markus T1 - Decoupling of neural network calibration measures T2 - German Conference on Pattern Recognition (GCPR) 2024 N2 - A lot of effort is currently invested in safeguarding autonomous driving systems, which heavily rely on deep neural networks for computer vision. We investigate the coupling of different neural network calibration measures with a special focus on the Area Under the Sparsification Error curve (AUSE) metric. We elaborate on the well-known inconsistency in determining optimal calibration using the Expected Calibration Error (ECE) and we demonstrate similar issues for the AUSE, the Uncertainty Calibration Score (UCS), as well as the Uncertainty Calibration Error (UCE). We conclude that the current methodologies leave a degree of freedom, which prevents a unique model calibration for the homologation of safety-critical functionalities. Furthermore, we propose the AUSE as an indirect measure for the residual uncertainty, which is irreducible for a fixed network architecture and is driven by the stochasticity in the underlying data generation process (aleatoric contribution) as well as the limitation in the hypothesis space (epistemic contribution). Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50104 PB - arXiv ER - TY - JOUR A1 - Jakab, Daniel A1 - Barthel, Julian A1 - Braun, Alexander A1 - Mohandas, Reenu A1 - Deegan, Brian Michael A1 - Kumbham, Mahendar A1 - Molloy, Dara A1 - Collins, Fiachra A1 - Scanlan, Anthony A1 - Eising, Ciarán T1 - SOLAS: Superpositioning an Optical Lens in Automotive Simulation JF - Electronic Imaging Y1 - 2025 U6 - https://doi.org/10.2352/EI.2025.37.15.AVM-101 SN - 2470-1173 VL - 37 IS - 15 SP - 101 EP - 1 PB - Society for Imaging Science & Technology ER - TY - JOUR A1 - Müller, Patrick A1 - Braun, Alexander A1 - Keuper, Margret T1 - Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models JF - IEEE Transactions on Pattern Analysis and Machine Intelligence KW - Optical imaging KW - Lenses KW - Robustness KW - Kernel KW - Optical sensors Y1 - 2025 U6 - https://doi.org/10.1109/TPAMI.2025.3622234 SN - 0162-8828 SP - 1 EP - 15 PB - IEEE ER - TY - INPR A1 - Wolf, Dominik Werner A1 - Braun, Alexander A1 - Ulrich, Markus T1 - Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration T2 - International Journal of Computer Vision (IJCV) N2 - 'A trustworthy representation of uncertainty is desirable and should be considered as a key feature of any machine learning method' (Huellermeier and Waegeman, 2021). This conclusion of Huellermeier et al. underpins the importance of calibrated uncertainties. Since AI-based algorithms are heavily impacted by dataset shifts, the automotive industry needs to safeguard its system against all possible contingencies. One important but often neglected dataset shift is caused by optical aberrations induced by the windshield. For the verification of the perception system performance, requirements on the AI performance need to be translated into optical metrics by a bijective mapping (Braun, 2023). Given this bijective mapping it is evident that the optical system characteristics add additional information about the magnitude of the dataset shift. As a consequence, we propose to incorporate a physical inductive bias into the neural network calibration architecture to enhance the robustness and the trustworthiness of the AI target application, which we demonstrate by using a semantic segmentation task as an example. By utilizing the Zernike coefficient vector of the optical system as a physical prior we can significantly reduce the mean expected calibration error in case of optical aberrations. As a result, we pave the way for a trustworthy uncertainty representation and for a holistic verification strategy of the perception chain. Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50120 PB - arXiv ER - TY - INPR A1 - Geerkens, Simon A1 - Sieberichs, Christian A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - QI2 -- an Interactive Tool for Data Quality Assurance N2 - The importance of high data quality is increasing with the growing impact and distribution of ML systems and big data. Also the planned AI Act from the European commission defines challenging legal requirements for data quality especially for the market introduction of safety relevant ML systems. In this paper we introduce a novel approach that supports the data quality assurance process of multiple data quality aspects. This approach enables the verification of quantitative data quality requirements. The concept and benefits are introduced and explained on small example data sets. How the method is applied is demonstrated on the well known MNIST data set based an handwritten digits. KW - Data Structures and Algorithms KW - Machine Learning KW - Computers and Society KW - Artificial Intelligence Y1 - 2023 PB - arXiv ER - TY - INPR A1 - Sieberichs, Christian A1 - Geerkens, Simon A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - ECS -- an Interactive Tool for Data Quality Assurance N2 - With the increasing capabilities of machine learning systems and their potential use in safety-critical systems, ensuring high-quality data is becoming increasingly important. In this paper we present a novel approach for the assurance of data quality. For this purpose, the mathematical basics are first discussed and the approach is presented using multiple examples. This results in the detection of data points with potentially harmful properties for the use in safety-critical systems. KW - Artificial Intelligence KW - Machine Learning KW - PrePrint KW - Systems and Control Y1 - 2023 U6 - https://doi.org/10.48550/arXiv.2307.04368 PB - arXiv ER - TY - JOUR A1 - Geerkens, Simon A1 - Sieberichs, Christian A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - QI²: an interactive tool for data quality assurance JF - AI and Ethics N2 - The importance of high data quality is increasing with the growing impact and distribution of ML systems and big data. Also, the planned AI Act from the European commission defines challenging legal requirements for data quality especially for the market introduction of safety relevant ML systems. In this paper, we introduce a novel approach that supports the data quality assurance process of multiple data quality aspects. This approach enables the verification of quantitative data quality requirements. The concept and benefits are introduced and explained on small example data sets. How the method is applied is demonstrated on the well-known MNIST data set based an handwritten digits. KW - Performance metrics KW - HSD Publikationsfonds KW - DEAL KW - DFG Publikationskosten KW - Machine learning KW - Quality assurance KW - Data integrity KW - Data quality Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-42945 SN - 2730-5961 N1 - Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 532148125 and supported by the central publication fund of Hochschule Düsseldorf University of Applied Sciences VL - 4 SP - 141 EP - 149 PB - Springer Nature ER - TY - JOUR A1 - Sieberichs, Christian A1 - Geerkens, Simon A1 - Braun, Alexander A1 - Waschulzik, Thomas T1 - ECS: an interactive tool for data quality assurance JF - AI and Ethics N2 - With the increasing capabilities of machine learning systems and their potential use in safety-critical systems, ensuring high-quality data is becoming increasingly important. In this paper, we present a novel approach for the assurance of data quality. For this purpose, the mathematical basics are first discussed and the approach is presented using multiple examples. This results in the detection of data points with potentially harmful properties for the use in safety-critical systems. KW - DEAL KW - HSD Publikationsfonds KW - Data visulization KW - Distance based KW - Data quality assurance KW - Equivalence class sets KW - DFG Publikationskosten Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-42908 SN - 2730-5961 N1 - Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 532148125 and supported by the central publication fund of Hochschule Düsseldorf University of Applied Sciences VL - 4 SP - 131 EP - 139 PB - Springer Nature ER - TY - JOUR A1 - Jakab, Daniel A1 - Braun, Alexander A1 - Agnew, Cathaoir A1 - Mohandas, Reenu A1 - Deegan, Brian Michael A1 - Molloy, Dara A1 - Ward, Enda A1 - Scanlan, Anthony A1 - Eising, Ciarán T1 - SS-SFR: synthetic scenes spatial frequency response on Virtual KITTI and degraded automotive simulations for object detection JF - IET Conference Proceedings Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-50080 SN - 2732-4494 VL - 2024 IS - 10 SP - 110 EP - 117 PB - Institution of Engineering and Technology (IET) ER - TY - JOUR A1 - Jakab, Daniel A1 - Vázquez, Joel Herrera A1 - Barthel, Julian A1 - Honsbrok, Jan A1 - Deegan, Brian A1 - Mohandas, Reenu A1 - Brophy, Tim A1 - Scanlan, Anthony A1 - Ward, Enda A1 - Collins, Fiachra A1 - Eising, Ciarán A1 - Braun, Alexander T1 - SOLAS 1.1: Automotive Optical Simulation in Computer Vision (Early Access) JF - IEEE Open Journal of Vehicular Technology KW - Optical imaging KW - Optical distortion KW - Cameras KW - Lenses KW - Automotive engineering KW - Adaptive optics KW - Object detection KW - Computer vision KW - Optical sensors KW - Production Y1 - 2025 U6 - https://doi.org/10.1109/OJVT.2025.3640419 SN - 2644-1330 N1 - The supplemental material contains material to support the article. DOI:10.1109/OJVT.2025.3640419/mm1 SP - 1 EP - 16 PB - Institute of Electrical and Electronics Engineers ER -