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 16 of 16 for “"Cross-Domain Generalization"”.
-
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.
-
Learning dense prediction: from correspondence to segmentation
… of labeled data for training, and iv) the poor cross-domain generalization to novel datasets.</p> <p>This integrated thesis focuses on dense prediction tasks, from correspondence estimation (stereo matching and optical flow) to 2D/3D semantic segmentation. Seven robust deep neural network models …
-
Advancing Cross-Domain Fake News Detection: Enhanced Models to Improve Generalization and Tackle the Class Imbalance Problem
The rapid proliferation of fake news across domains, such as politics, health, and social media, poses a significant threat to the integrity of information dissemination, leading to misinformation that can affect public perception and decision-making. Detecting fake news is critical to preserving …
-
Building Trust in AI: Auditing Consistency and Generalization in Large Language Models
… deployed tools in high-stakes professional domains such as law, medicine, and finance. Their ability to perform complex reasoning, generate human-like responses, and support decision-making promises transformative gains in efficiency and accessibility. Yet beneath strong benchmark …
-
Detection of Ongoing GPS Spoofing Using A Convolutional Neural Network
… when training and testing on data from the same domain, achieving balanced-accuracy scores of 99 % on targeted scenarios. Cross-domain generalization to datasets with different parameters decreases noticeably, with performance dropping to nearrandom- guessing levels. The study also provides …
-
Using Align and Distill in Object Detection of Security X-ray Images.
Domain adaptation in object detection is critical for real-world applications where distribution shifts degrade model performance. Security X-ray imaging presents a unique challenge due to variations in scanning devices and environmental conditions, leading to significant domain discrepancies. To …
-
Phonological development in twins after non-linear phonological and morphosyntactic intervention
… changes after morphosyntax treatment (cross-domain generalization), after phonological treatment (direct treatment effect), and after the full 16 weeks (overall effects and treatment order effect). Specific changes within the phonological systems of the twins were interpreted from a …
-
Data Efficient Deep Learning for Rolling Element Bearing Fault Diagnosis
… and efficiently loaded data can deliver superior cross domain generalization even with limited samples. Benchmark publicly available bearing datasets are analyzed, revealing weak cross domain coverage that restrict the transferability of ML models to industrial scenarios. To address this gap, a …
-
Discriminative and Generative Video Modeling
… of modern computer vision, enabling progress in domains such as surveillance, autonomous driving, and instructional assistance. Yet the complexity of spatiotemporal dynamics, multimodal integration, and the need for scalable and generalizable models present significant challenges. This …
-
Proficiency modeling and skill extraction in BPM education: a generative AI-supported framework
… competencies and skills, derived from structured domain-specific content. To resolve the second, it establishes a mathematically grounded proficiency architecture for each stage of learning, providing formal support for diagnostic, formative, and summative assessments powered by Intelligent …
-
AI-Driven Vehicle Re-Identification: Decoding Effective Features through Ablation Studies
… locations, under varying viewpoints, and across diverse environmental conditions. Humans are generally able to identify vehicles based on unique features such as shape, color, and distinctive markings. However, translating this ability into an automated system poses significant challenges …
-
Robust and Interpretable Cross-Domain Arabic Readability Prediction Using Hybrid Modeling: Evidence on the Limitations of Transformer-Based Classifiers
… concept of readability has been widely studied across languages due to its significant impact on reading comprehension, leading to the development of various methods and approaches. In this study, I addressed two key challenges in readability assessment. First, I examine the performance of …
-
Beyond images: fetal ultrasound video understanding for detecting congenital heart diseases
… data scarcity, privacy constraints, and cross-domain generalization through large-scale self-supervised learning. We propose Sparse Tube Ultrasound Distillation (STUD), together with a divergence-guided model merging strategy, for decentralized anomaly detection across clinical sites …
-
Towards Generalizable Open-World Robot Manipulation by Training with Off-Domain Data
Achieving generalization in open-world robotic manipulation is a critical step toward deploying autonomous agents in dynamic, unstructured environments. However, learning manipulation skills that generalize to unseen objects, layouts, and natural language instructions remains challenging, …
-
Label-Efficient Visual Understanding with Consistency Constraints
… networks to produce consistent predictions across different transformations (\eg geometry, temporal, photometric, etc.). We organize the dissertation as follows. In Part I, we propose to use the consistency over different geometric formulations and a cycle consistency over time to tackle the …