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 171 for “"Domain Shift"”.
-
Compositional and adaptive visual recognition under domain shift
… Third, inference should adapt to the input, domain, or task without requiring full retraining or access to target-domain supervision. The thesis develops architectures and learning strategies that encourage part–whole and region-level structure; training-free and few-shot inference methods …
-
Handling Domain Shift in 3D Point Cloud Perception
This thesis addresses the problem of domain shift in 3D point cloud perception. In the last decades, there has been tremendous progress in within-domain training and testing. However, the performance of perception models is affected when training on a source domain and testing on a target domain …
-
Uncertainty-Aware Adaptation for Simultaneous Machine Translation under Domain Shift
… However, these systems are highly sensitive to domain shift, where discrepancies between training and deployment data can significantly degrade performance. This paper proposes an uncertainty-aware SiMT framework that detects and adapts to domain shift in real-time. The system uses a neural …
-
Dealing with domain shift in deep learning: from training-time generalization to test-time adaptation
… Specifically, it investigates two directions: Domain Generalization (DG), which aims to learn domain-invariant representations during training, and Test-Time Adaptation (TTA), which adjusts models dynamically during inference using only unlabeled test data. Together, these approaches address …
-
Automated LiDAR-Camera Calibration for Autonomous Driving under Domain Shift due to Changing Weather Conditions
Thesis (M.S.)--Michigan State University. Electrical and Computer Engineering - Master of Science, 2026
-
THE CHALLENGE OF DOMAIN SHIFT IN REAL-WORLD ROBOTIC VISION: TOWARD SCALABLE, UNSUPERVISED, AND CLOUD-BASED ADAPTATION
… important limitations caused by the so-called domain shift problem: being trained on simulated or generic datasets (source domain), deep neural networks dramatically fail to tackle the complexity of the real-world environments (target domain) in which the robots operate. This dissertation …
-
Human action recognition in the real world: handling domain shift in open-set, source-free and multi-source scenarios
… to adapting models to visual and semantic domains potentially very different from those characterizing the data used to train them. Formally, this task goes by the name of Domain Adaptation (DA), and it has recently been devoted a significant amount of effort. While image-based content has …
-
The Conversion of Bifidobacterium adolescentis Sucrose Phosphorylase into a Polyphenol Transglucosidase via Structure-based Enzyme Engineering
… was obtained and it displayed an unexpected shift of an entire domain by 3.3 Å. A crystal structure of BaSP D192N-Q345F, an inactive variant in complex with resveratrol-3-α-D-glucosid, the glucosylation product of resveratrol, synthesized by BaSP Q345F was solved. It proved that the domain …
-
Domain Adaptation for Automated Program Repair
… all these methods are limited with respect to Domain Shift. In other words, APR models are trained and tested on the same set of projects (i.e., when fixing a bug from project A, the model has already seen example fixed bugs from project A in the training set). However, in the real world, APR …
-
Unsupervised Domain Adaptation for Object Counting
… by having plant image datasets with significant domain shift due to different experimental conditions, e.g. applying an annotated dataset of indoor plant images for use on outdoor images, or on a different plant species. Learning to count from synthetic data to apply the knowledge in real-world …
-
Developing Transferable Deep Models for Mobile Health
… mHealth studies. The first is the problem of domain shift where the data distribution varies across studies. This would result in models trained on one study to have sub-optimal performance on a different study. Domain shift is common in wearable sensor data since there are several sources of …
-
Representation learning for domain adaptation and cross-modal retrieval
Most machine learning applications involve a domain shift between data on which a model has initially been trained and data from a similar but different domain to which the model is later applied on. Applications range from human computer interaction (e.g., humans with different characteristics for …
-
Semi-Supervised Galaxy Morphology Classification Using Convolutional Vision Transformers
… galaxy evolution, but modern high-redshift surveys such as JADES produce a large number of unlabeled images that cannot be handled with traditional manual or supervised learning methods. This work explores a semi-supervised transfer learning framework that leverages labeled data from …
-
Manifold Based Deep Learning: Advances and Machine Learning Applications
… reduction, subspace learning, visual domain adaptation, clustering, and more. In this dissertation, we propose a framework for linear dimensionality reduction called the proxy matrix optimization (PMO) that uses the Grassmann manifold for optimizing over orthogonal matrix manifolds. …
-
Domain adaptive learning with disentangled features
… the knowledge learned from a rich-labeled source domain to a scarce-labeled target domain. However, the performance of deep learning models degrades significantly when testing on novel domains due to the presence of domain shift. To tackle the domain shift, conventional domain adaptation methods …
-
Automatic white matter bundle segmentation in glioma patients
… dataset of glioma patients. We categorized the domain shift between healthy controls and glioma patients into two types: systematic domain shift (stemming from differences in acquisition and preprocessing) and tumor-related shift (arising from pathological anatomical changes). We developed …
Page 1 of 9