1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-29558
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorSchwenker, Friedhelm-
dc.contributor.advisorStadelmann, Thilo-
dc.contributor.advisorJaggi, Martin-
dc.contributor.authorAmirian, Mohammadreza-
dc.date.accessioned2024-01-10T16:04:02Z-
dc.date.available2024-01-10T16:04:02Z-
dc.date.issued2023-
dc.identifier.otherurn:nbn:de:bsz:289-oparu-51540-1de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/29558-
dc.description.abstractRecent breakthroughs in machine and deep learning (ML and DL) research have provided excellent tools for leveraging enormous amounts of data and optimizing huge models with millions of parameters to obtain accurate networks for image processing. These developments open up tremendous opportunities for using artificial intelligence (AI) in the automation and human assisted AI industry. However, as more and more models are deployed and used in practice, many challenges have emerged. This thesis presents various approaches that address robustness and explainability challenges for using ML and DL in practice. Robustness and reliability are the critical components of any model before certification and deployment in practice. Deep convolutional neural networks (CNNs) exhibit vulnerability to transformations of their inputs, such as rotation and scaling, or intentional manipulations as described in the adversarial attack literature. In addition, building trust in AI-based models requires a better understanding of current models and developing methods that are more explainable and interpretable a priori. This thesis presents developments in computer vision models' robustness and explainability. Furthermore, this thesis offers an example of using vision models' feature response visualization (models' interpretations) to improve robustness despite interpretability and robustness being seemingly unrelated in the related research. Besides methodological developments for robust and explainable vision models, a key message of this thesis is introducing model interpretation techniques as a tool for understanding vision models and improving their design and robustness. In addition to the theoretical developments, this thesis demonstrates several applications of ML and DL in different contexts, such as medical imaging and affective computing.de_CH
dc.format.extentXIV, 150de_CH
dc.language.isoende_CH
dc.publisherUniversität Ulmde_CH
dc.rightshttp://creativecommons.org/licenses/by-nc-nd/4.0/de_CH
dc.subjectMachine learningde_CH
dc.subjectRobust controlde_CH
dc.subjectDeep learningde_CH
dc.subjectConvolutional neural network (CNN)de_CH
dc.subjectVision transformer (ViT)de_CH
dc.subjectRobustnessde_CH
dc.subjectExplainabilityde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.titleDeep learning for robust and explainable models in computer visionde_CH
dc.typeDissertationde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitCentre for Artificial Intelligence (CAI)de_CH
dc.identifier.doi10.18725/OPARU-51464de_CH
dc.identifier.doi10.21256/zhaw-29558-
zhaw.originated.zhawYesde_CH
zhaw.webfeedMachine Perception and Cognitionde_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2023_Amirian_Dissertation_small.pdf2.86 MBAdobe PDFThumbnail
View/Open
Show simple item record
Amirian, M. (2023). Deep learning for robust and explainable models in computer vision [Doctoral dissertation, Universität Ulm]. https://doi.org/10.18725/OPARU-51464
Amirian, M. (2023) Deep learning for robust and explainable models in computer vision. Doctoral dissertation. Universität Ulm. Available at: https://doi.org/10.18725/OPARU-51464.
M. Amirian, “Deep learning for robust and explainable models in computer vision,” Doctoral dissertation, Universität Ulm, 2023. doi: 10.18725/OPARU-51464.
AMIRIAN, Mohammadreza, 2023. Deep learning for robust and explainable models in computer vision. Doctoral dissertation. Universität Ulm
Amirian, Mohammadreza. 2023. “Deep Learning for Robust and Explainable Models in Computer Vision.” Doctoral dissertation, Universität Ulm. https://doi.org/10.18725/OPARU-51464.
Amirian, Mohammadreza. Deep Learning for Robust and Explainable Models in Computer Vision. Universität Ulm, 2023, https://doi.org/10.18725/OPARU-51464.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.