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 19 of 19 for “"Domain Shift"”.
-
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 …
-
Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation
We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling …
-
Evaluating the Role of Balanced Causal and Non-Causal Features in Predictive Modeling
… models that provides a stable performance across domains unseen during training, remains a persistent challenge. This generalizability of models is particularly challenging when the relationship between input features and target labels varies across domains. This study is motivated by recent work …
-
Enhancing Breast Cancer Detection Through Combination of Contrastive Learning and Adversarial Domain Adaptation
… lack of being adaptable to new or different data domains. This thesis uses cutting-edge deep learning methods to address these issues. We use self-supervised learning techniques like Bootstrap Your Own Latent (BYOL) and Simple Framework for Contrastive Learning of Visual Representations (SimCLR) …
-
Uncertainty-aware fusion of foundation and task-specific models for cardiac MRI segmentation
… (CNN)-based models achieve high accuracy on domain-specific data but struggle to generalize to unseen data. To address these complementary limitations, we propose an uncertainty-aware fusion framework that integrates the generalizability of foundation models with the anatomical precision of …
-
Essays on Optimal Transport Theory and Causal Inference: A Theoretical and Empirical Approach
… have non-overlap support. We make a natural domain shift assumption for the non-overlap region based on the optimal transport theory. We study the identification of average treatment effects for the nonoverlap region and propose three-step estimators of the average treatment effect and …
-
Empowering vision machine perception for robust telehealth applications
… (TTA) techniques offer promise in handling domain-shift challenges during ML model deployment, they are susceptible to error accumulation and even adversarial attack. We extensively investigate this issue, resulting in the introduction of “persistent TTA” and “reusing of incorrect prediction …
-
Better Generalization with Less Human Annotation Using Meta-Learning and Self-Supervised Learning for Image Analysis
… is difficult to obtain in medical or geophysical domains due to many reasons, including the high annotation cost, privacy concerns, and physical constraints. To address the data efficiency issue in training the deep learning model, we proposed the solutions in two directions: meta-learning and …
-
Towards robust and domain invariant feature representations in Deep Learning
… Improving generalization of neural nets across domains. The first part of the dissertation approaches the problem of robustness from two broad viewpoints: Robustness to external nuisance factors that occur in the data and robustness (or a lack thereof) to perturbations of the learned feature …
-
Semi-supervised detection of industrial fouling using ultrasound
… methods to detect and counter the so-called domain shift that occurs when experimenting in the physical world, and provide experimental evidence that our methods work in practice.
-
Learning to Adapt Neural Networks Across Visual Domains
… and so on, which is also popularly known as domain-shift. In order to make a classifier cope with such domain-shifts, a sub-field in machine learning called domain adaptation (DA) has emerged that jointly uses the annotated data from the source domain together with the unlabelled data from …
-
Learning without Labels - Reducing Supervision in Training, Inference, and Evaluation of Deep Neural Networks
… focusing on Source-Free Unsupervised Domain Adaptation scenarios in visual tasks such as Facial Expression Recognition and video-based Action Recognition, primarily leveraging self-supervision and self-training. At inference, we address the challenge of removing fixed output …
-
VISUAL AND SEMANTIC KNOWLEDGE TRANSFER FOR NOVEL TASKS
… is aimed at using data from the \emph{source} domain to improve the performance of a model on the \emph{target} domain, and these two domains have different data or different tasks. One specific case of transfer learning is Zero-Shot Learning. It deals with the situation where \emph{source} …
-
IMPROVING PERFORMANCE OF INTRUSION DETECTION SYSTEMS FOR SOFTWARE-DEFINED NETWORKS
… and programmability. However, this architectural shift also exposes SDNs to a wide range of security threats, making them highly susceptible to sophisticated and dynamic cyberattacks. Traditional Intrusion Detection Systems (IDSs), often designed for static and monolithic network architectures, …
-
Advanced Computational Holography for Perceptual Enhancement and Application in HUDs
… intensity weighting and a dynamic range shift that selectively suppresses noise in perceptually sensitive areas. As a result, the method achieves superior contrast ratios and produces sharper and more vivid reconstructed holographic images with faster convergence. The optical …
-
Dynamically Instance-Guided Adaptation: A Backward-free Approach for Test-Time Domain Adaptive Semantic Segmentation
… models often fail when deployed in new target domains due to domain shifts. Test-Time Domain Adaptation for Semantic Segmentation (TTDA-Seg) aims to adapt models efficiently during inference without target labels, but existing methods struggle with efficiency (requiring backward optimization) …
-
Efficient Distributed and Multi-Modal Machine Learning in Wireless Networks
… data. In the second stage, collaborative domain adaptation is proposed to leverage the wireless environment knowledge of multiple BSs to guide under-performing BSs under domain shift. The results showcase that the proposed frameworks require significantly smaller amount of data and …
-
Addressing Distributional Shift challenges in Computer Vision for Real-World Applications
L'abstract è presente nell'allegato / the abstract is in the attachment