Enhancement of the domain generalization of vision transformers through advanced data augmentation techniques

Froudakis, Evangelos; Φρουδάκης, Ευάγγελος

dc.contributor.author	Froudakis, Evangelos	en
dc.contributor.author	Φρουδάκης, Ευάγγελος	el
dc.date.accessioned	2024-12-10T08:43:35Z
dc.date.available	2024-12-10T08:43:35Z
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/60514
dc.identifier.uri	http://dx.doi.org/10.26240/heal.ntua.28210
dc.rights	Default License
dc.subject	Neural networks	en
dc.subject	Deep learning	en
dc.subject	Image segmentation	en
dc.subject	Domain generalization	en
dc.subject	Style transfer	en
dc.subject	Data augmentation	en
dc.title	Enhancement of the domain generalization of vision transformers through advanced data augmentation techniques	en
heal.type	bachelorThesis
heal.classification	Computer science	en
heal.language	el
heal.language	en
heal.access	free
heal.recordProvider	ntua	el
heal.publicationDate	2024-07-09
heal.abstract	Domain generalization is a critical challenge in medical imaging, where the performance of deep learning models can significantly degrade due to domain shifts—variations in data distribution caused by differences in imaging protocols, equipment, or patient populations. This issue is particularly problematic in medical image segmentation, where models trained on a specific dataset often fail to generalize to new, unseen data, limiting their practical applicability in clinical settings. Addressing this problem requires innovative techniques to enhance model robustness and generalizability. This thesis investigates the enhancement of domain generalization in medical image segmentation through advanced data augmentation techniques. This study focuses on evaluating the impact of data augmentation at both the input and feature levels using methods such as style-based augmentation. By incorporating these augmentation strategies, the goal is to improve the ability of models to handle unseen variations in medical images, thereby increasing their robustness and reliability in real-world applications. In the experiments, a vision transformer model was fine-tuned with datasets augmented through a combination of style-based and other input-level augmentation methods. These techniques enhance the diversity of training data, allowing the model to learn robust features that are less sensitive to various types of data shifts. The evaluation was conducted on prostate MRI datasets as the in-domain data and six additional datasets as the out-of-distribution domains. The results demonstrated that models trained with augmented data exhibited significantly improved robustness and generalization to OOD samples. The combination of style- based and other augmentation methods led to a notable increase in generalizability. This suggests that integrating complex data augmentation techniques can significantly enhance the robustness of medical image segmentation models, making them more reliable for clinical applications.	en
heal.advisorName	Voulodimos, Athanasios	en
heal.committeeMemberName	Stamou, Georgios	en
heal.committeeMemberName	Voulodimos, Athanasios	en
heal.committeeMemberName	Stafylopatis, Andreas-Georgios	en
heal.academicPublisher	Εθνικό Μετσόβιο Πολυτεχνείο. Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών. Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών	el
heal.academicPublisherID	ntua
heal.numberOfPages	87 σ.	el
heal.fullTextAvailability	false
heal.fullTextAvailability	false