@inproceedings{MuellerBraunKeuper2022, author = {M{\"u}ller, Patrick and Braun, Alexander and Keuper, Margret}, title = {Impact of realistic properties of the point spread function on classification tasks to reveal a possible distribution shift}, series = {NeurIPS 2022: Workshop on Distribution Shifts: Connecting Methods and Applications, December 3rd, 2022, New Orleans, USA}, booktitle = {NeurIPS 2022: Workshop on Distribution Shifts: Connecting Methods and Applications, December 3rd, 2022, New Orleans, USA}, publisher = {NeurIPS}, address = {New Orleans}, year = {2022}, language = {en} } @inproceedings{MuellerBraunKeuper2023, author = {M{\"u}ller, Patrick and Braun, Alexander and Keuper, Margret}, title = {Classification robustness to common optical aberrations}, series = {2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}, booktitle = {2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}, publisher = {IEEE}, doi = {10.1109/ICCVW60793.2023.00391}, pages = {3634 -- 3645}, year = {2023}, subject = {Maschinelles Sehen}, language = {en} } @unpublished{MuellerBraunKeuper2025, author = {M{\"u}ller, Patrick and Braun, Alexander and Keuper, Margret}, title = {Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models}, edition = {v1}, publisher = {arXiv}, doi = {10.48550/arXiv.2504.18510}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-55457}, pages = {32}, year = {2025}, abstract = {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.}, subject = {Maschinelles Lernen}, language = {de} } @article{MuellerBraunKeuper2025, author = {M{\"u}ller, Patrick and Braun, Alexander and Keuper, Margret}, title = {Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models}, series = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, publisher = {IEEE}, issn = {0162-8828}, doi = {10.1109/TPAMI.2025.3622234}, pages = {1 -- 15}, year = {2025}, language = {en} }