Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 117 for “"Domain generalization"”.
-
Advancing Domain Generalization Through Diverse Training Strategies
… often suffer performance degradation due to domain shift, where discrepancies exist between training and testing data distributions. Domain Generalization (DG) addresses this problem by leveraging information from multiple source domains to improve a model’s ability to generalize to unseen …
-
Adaptive Domain Generalization for Digital Pathology Images
In AI-based histopathology, domain shifts are common and well-studied. However, this research focuses on stain and scanner variations, which do not show the full picture– shifts may be combinations of other shifts, or “invisible” shifts that are not obvious but still damage performance of machine …
-
Visual Domain Generalization via Self-Supervised Learning
L'abstract è presente nell'allegato / the abstract is in the attachment
-
A multimodal approach towards video domain generalization
Στις μέρες μας, ένας παράγοντας κλειδί για την τεχνολογική ευημερία και ανάπτυξη της ανθρωπότητας είναι η τεχνητή νοημοσύνη. Εφαρμογές τεχνητής νοημοσύνης μπορούν να βρεθούν σε πολλούς τομείς της επιστήμης υπολογιστών, αλλά και της επιστήμης γενικότερα, όπως είναι η επεξεργασία φυσικής γλώσσας και …
-
Domain Generalization and its Application in Deepfake Detection
… test environments. This thesis aims to ease the generalization problem from both the general machine learning and specific downstream application perspectives. For general machine learning systems, we propose two effective domain generalization (DG) methods given different settings where training …
-
Efficient invariant feature subspace recovery for domain generalization
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
Domain generalization in vision models for aerial imagery datasets
… with a real dataset can serve as a syn-to-real generalization benchmark, (2) SKYSCAPES synthetic data can augment real-data for better generalization and (3) intra-source weather and daytime variations in SKYSCAPES can be used to systematically study robustness of aerial vision models. We hope …
-
Domain Generalization for Semantic Segmentation of Aerial Imagery Datasets
Since curating large datasets with dense annotations from UAVs under diverse weather, daytime and layout conditions in the real-world is restrictive due to several prohibitive constraints (sampling images from same locations under different conditions, annotation cost, etc.), we propose using …
-
Gradual domain generalization for visible-infrared person re-identification
… challenges arise from the substantial domain gap between modalities, resulting in pronounced discrepancies in appearance, texture, and illumination. This gap severely hampers the generalization ability of deep learning models, leading to degraded cross-modal retrieval performance. …
-
Domain generalization for sequential data via invariant subspace recovery
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Domain Generalization and Adaptation with Generative Modeling and Representation Learning
… but from the significantly different visual domain. Many approaches have been proposed in both of these settings, however, not many other works focus on the generative modeling in this context, neither focus on studying the structure of hidden representations learned by the deep learning …
-
Cross-domain generalization for robust spatial gene expression prediction from histopathology slides
The full abstract for this thesis is available in the body of the thesis, and will be available when the embargo expires.
-
Extending an invariant models method to domain generalization settings in ecological data
… (predictive) settings. A method proposed for a domain generalization setting is extended to include linear mixed-effect models, a common class of models used in ecological settings. The invariant models method is based on selecting models which produce independent residuals across tasks, …
-
On the study of various methods for domain generalization and inverse problems
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Addressing Data Scarcity in Domain Generalization for Computer Vision Applications in Image Classification
Domain generalization (DG) for image classification is a crucial task in machine learning that focuses on transferring domain-invariant knowledge from multiple source domains to an unseen target domain. Traditional DG methods assume that classes of interest are present across multiple domains …
-
Enhancing Domain Generalization in Histopathology Image Classification through Deep Learning and Generative-AI Methods
… clinical environments remains challenging due to domain shift problem—the discrepancy between the data distribution used for training and the data encountered during deployment. This issue is especially pronounced in histopathology image classification, where variations in acquisition pipelines …
Page 1 of 6