{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:30:21Z","timestamp":1790879421599,"version":"4.1.0"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DFG","award":["DFG-FOR 5336"],"award-info":[{"award-number":["DFG-FOR 5336"]}]},{"name":"Learning to Sense"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpami.2025.3622234","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:37:14Z","timestamp":1760636234000},"page":"2139-2153","source":"Crossref","is-referenced-by-count":5,"title":["Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9585-6723","authenticated-orcid":false,"given":"Patrick","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"University of Siegen, Siegen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8358-0578","authenticated-orcid":false,"given":"Alexander","family":"Braun","sequence":"additional","affiliation":[{"name":"Hochschule Düsseldorf, University of Applied Sciences, Düsseldorf, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8437-7993","authenticated-orcid":false,"given":"Margret","family":"Keuper","sequence":"additional","affiliation":[{"name":"University of Mannheim, Mannheim, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139644181"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9783527699254"},{"key":"ref3","volume-title":"Modern Optical Engineering: The Design of Optical Systems","author":"Smith","year":"2000"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1201\/9781315217635"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1117\/3.2691089"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1515\/teme-2022-0029"},{"key":"ref7","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref8","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019"},{"key":"ref9","first-page":"18963","article-title":"3D common corruptions and data augmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kar","year":"2022"},{"key":"ref10","article-title":"Examining the impact of blur on recognition by convolutional networks","author":"Vasiljevic","year":"2016"},{"key":"ref11","first-page":"3632","article-title":"Classification robustness to common optical aberrations","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. Workshops","author":"M\u00fcller"},{"key":"ref12","article-title":"OpticStudio optical, illumination & laser system design software - zemax","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref15","first-page":"11618","article-title":"nuScenes: A multimodal dataset for autonomous driving","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Caesar"},{"key":"ref16","first-page":"1022","article-title":"Benchmarking robustness of 3D object detection to common corruptions","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Dong"},{"key":"ref17","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Croce"},{"key":"ref18","first-page":"2574","article-title":"DeepFool: A simple and accurate method to fool deep neural networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Moosavi-Dezfooli"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref21","article-title":"Robustbench: A standardized adversarial robustness benchmark","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Croce"},{"key":"ref22","article-title":"Is robustbench\/autoattack a suitable benchmark for adversarial robustness?","volume-title":"Proc. AAAI-22 Workshop Adversarial Mach. Learn. Beyond","author":"Lorenz"},{"key":"ref23","first-page":"91","article-title":"Improving robustness using generated data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Gowal"},{"key":"ref24","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos"},{"key":"ref25","first-page":"113","article-title":"AutoAugment: Learning augmentation strategies from data","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Cubuk"},{"key":"ref26","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2020"},{"key":"ref27","first-page":"8320","article-title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Hendrycks"},{"key":"ref28","first-page":"10191","article-title":"Improving robustness against common corruptions with frequency biased models","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Saikia"},{"key":"ref29","first-page":"3533","article-title":"Do adversarially robust ImageNet models transfer better?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Salman"},{"key":"ref30","article-title":"Imagenet-patch: A dataset for benchmarking machine learning robustness against adversarial patches","volume-title":"Pattern Recognit.","volume":"134","author":"Pintor","year":"2023"},{"issue":"7","key":"ref31","first-page":"689","article-title":"Beugungstheorie des schneidenver-fahrens und seiner verbesserten form, der phasenkontrastmethode","volume-title":"Physica","volume":"1","author":"Zernike"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-1313.2009.00662.x"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/10.900255"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1201\/9780849382796"},{"issue":"10","key":"ref35","article-title":"Direct determination of aberration functions in microscopy by an artificial neural network","volume-title":"Opt. Express","volume":"28","author":"Cumming","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1051\/0004-6361\/201219797"},{"issue":"32","key":"ref37","article-title":"Wave-front reconstruction using a Shack\u2013Hartmann sensor","volume-title":"Appl. Opt.","volume":"31","author":"Lane","year":"1992"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01352"},{"key":"ref39","article-title":"3D PSF models for fluorescence microscopy in ImageJ","volume-title":"Proc. 12th Int. Conf. Methods Appl. Fluorescence Spectrosc. Imag. Probes","author":"Kirshner"},{"key":"ref40","doi-asserted-by":"crossref","volume-title":"Camera Image Quality Benchmarking","author":"Phillips","DOI":"10.1002\/9781119054504"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/3527606688"},{"key":"ref42","volume-title":"Optics","author":"Hecht","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/9783527699247"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1117\/12.279513"},{"key":"ref45","volume-title":"Introduction to Fourier Optics","author":"Goodman","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1117\/3.419857"},{"key":"ref47","first-page":"242-1","article-title":"Correcting misleading image quality measurements","volume-title":"Electron. Imag.","volume":"2020","author":"Koren","year":"2020"},{"key":"ref48","volume-title":"Digital Image Processing","author":"Gonzalez","year":"2009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3139\/9783446461260"},{"key":"ref50","article-title":"vision\/references\/classification.v0.11.0.pytorch\/vision"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref52","article-title":"Lens-designs","author":"Reiley"},{"issue":"19","key":"ref53","article-title":"3D-printed portable robotic mobile microscope for remote diagnosis of global health diseases","volume-title":"Electronics","volume":"10","author":"Garc\u0131\u00e1-Villena","year":"2021"},{"key":"ref54","article-title":"Torchvision 0.15"},{"key":"ref55","first-page":"6022","article-title":"CutMix: Regularization strategy to train strong classifiers with localizable features","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Yun"},{"key":"ref56","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref57","article-title":"NoisyMix: Boosting model robustness to common corruptions","author":"Erichson"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref59","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Huang"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref63","first-page":"12009","article-title":"Swin transformer v2: Scaling up capacity and resolution","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Liu"},{"key":"ref64","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tan"},{"key":"ref65","first-page":"12159","article-title":"Vision transformers for dense prediction","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Ranftl"},{"issue":"3","key":"ref66","first-page":"239","article-title":"The treatment of ties in ranking problems","volume-title":"Biometrika","volume":"33","author":"Kendall","year":"1945"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_33"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref71","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref72","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang"},{"key":"ref73","first-page":"936","article-title":"Feature pyramid networks for object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Lin"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref75","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Lin"},{"key":"ref76","article-title":"YOLOX: Exceeding YOLO series in 2021","author":"Ge","year":"2021"},{"key":"ref77","first-page":"9205","article-title":"Does robustness on ImageNet transfer to downstream tasks?","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Yamada"},{"key":"ref78","first-page":"13618","article-title":"Proper reuse of image classification features improves object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Vasconcelos"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref80","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Caron"},{"key":"ref81","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref82","article-title":"ConvNets match vision transformers at scale","author":"Smith"},{"key":"ref83","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref84","first-page":"779","article-title":"You only look once: Unified, real-time object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Redmon"},{"key":"ref85","doi-asserted-by":"crossref","article-title":"YOLO-world: Real-time open-vocabulary object detection","author":"Cheng","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref86","article-title":"MMDetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref87","first-page":"7363","article-title":"Grid R-CNN","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Lu"},{"key":"ref88","first-page":"9992","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Liu"},{"key":"ref89","article-title":"YOLOv3: An incremental improvement","author":"Redmon"},{"key":"ref90","first-page":"4969","article-title":"Hybrid task cascade for instance segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Chen"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref94","first-page":"9759","article-title":"Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1080\/09500340.2011.554896"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/MetroAutomotive54295.2022.9855079"},{"issue":"4","key":"ref97","first-page":"600","article-title":"Image quality assessment: From error visibility to structural similarity","volume-title":"IEEE Trans. Image Process.","volume":"13","author":"Wang","year":"2004"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2023.10205967"},{"key":"ref99","volume-title":"ISO12233:2017, Photography \u2014 Electronic Still Picture Imaging \u2014 Resolution and Spatial Frequency","year":"2017"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1117\/12.838698"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1117\/12.2004432"},{"key":"ref102","article-title":"Imatest target generator"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00271"},{"key":"ref104","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref105","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref106","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref107","first-page":"4015","article-title":"Segment anything","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Kirillov"},{"key":"ref108","article-title":"As large as it gets\u2013Studying infinitely large convolutions via neural implicit frequency filters","author":"Grabinski","year":"2024"},{"key":"ref109","article-title":"vision\/references\/detection at main pytorch\/vision"},{"key":"ref110","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"Goyal"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11372200\/11205303.pdf?arnumber=11205303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:57:17Z","timestamp":1770703037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11205303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":110,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3622234","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}