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 78 for “"DOMAIN-ADAPTIVE"”.
-
DOMAIN ADAPTIVE OBJECT RECOGNITION AND DETECTION
… training data from single or multiple "source" domains but wish to learn a classifier which performs well on a "target" domain with a different distribution and no labeled training data. In visual object detection, for example, where the goal is to locate the objects of interest in a given …
-
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 …
-
FAST ALGORITHMS FOR TRANSFORM DOMAIN ADAPTIVE FILTERS
In the field of adaptive signal processing, a wide variety of recursive algorithms have been developed in the literature for the implementation of adaptive filters. Among them, the least mean square (LMS) algorithm is the most popular one, due to its simplicity and robustness to finite word-length …
-
VLSI IMPLEMENTATION OF TRANSFORM DOMAIN ADAPTIVE FILTERS
… for effective implementation of transform domain adaptive filters (TDAF). It is called Generalized Sliding Transform processor ( GST processor) since it can be used for the implementation of a class of transforms called Generalized. Sliding Transform. The commonly used transforms, such as …
-
Accelerating scientific discovery using domain adaptive language modelling
… process and that the recent advances in the NLP domain provide us with a powerful methodological base, our work aims to establish methods that can speed up parts of the discovery process relying on scientific and technical corpora. We focus on but do not limit our work on patent corpora as …
-
Domain adaptive control architecture for advanced manufacturing systems
… study is to design, develop, and investigate domain adaptive control architecture for advanced manufacturing systems. The proposed control architecture is a swarm-based, multi-agent system that exhibits adaptive and emergent behavior that has been inspired from social insects, such as wasps. …
-
Domain-Adaptive Sentiment Analysis Across Online Social Networks
… time-consuming construction of prompts for cross-domain aspect term extraction. In this thesis, these challenges are tackled by employing several innovative deep neural network models. First, a novel and efficient framework is introduced for extracting aspect terms by combining contextual and …
-
DOMAIN ADAPTIVE 3D OBJECT DETECTION FOR AUTONOMOUS VEHICLES
Thesis (Ph.D.)--Michigan State University. Electrical and Computer Engineering - Doctor of Philosophy, 2025
-
ADVANCING DOMAIN ADAPTIVE POSE ESTIMATION: SOLUTIONS FOR EVOLVING CHALLENGES
… datasets due to scarce annotations creates a domain gap that degrades model performance. This thesis investigates domain adaptation solutions spanning UDA, TTA, and OTTA. For UDA, we enhance generalization by integrating depth maps with RGB inputs via multi-modal alignment in pre-training. For …
-
ENHANCING ZERO-SHOT SEGMENTATION WITH DOMAIN-ADAPTIVE PROMPT LEARNING
… such models still struggle to incorporate domain-specific knowledge and often require extensive learnable prompt engineering. This project aims to overcome these limitations by introducing domain-adaptive prompt learning into a CLIP-based ZSSeg pipeline. Our approach enhances CLIP-based …
-
A novel approach to multiple reference frequency domain adaptive control
Adaptive feedforward control of any physical system, acoustical, vibrational or other, requires what is termed as an uncontrollable coherent reference signal. That is, a signal which is highly representative (coherent) of the disturbance to be controlled which is not affected by the control …
-
Challenges in using existing domain adaptive techniques for real-world settings
… deployments of machine learning models. Domain Adaptation (DA) is a widely recognized paradigm to combat this. DA is a sub-field of machine learning that is explicitly concerned with designing algorithms to account for the distributional differences between sets of data. It involves …
-
Advancing Semi-Supervised Domain Adaptive Semantic Segmentation Through Effective Source Integration Strategies
… on fully labeled datasets. Semi-supervised domain adaptation (SSDA) further mitigates this issue by incorporating labeled data from a source domain alongside minimally labeled target data. While existing SSDA methods often underperform compared to fully supervised approaches, recent SSL …
-
Domain Adaptive Object Detection and Video Understanding from High Variance Remote Sensing Data
… While unsupervised and semi-supervised domain adaptation (DA) techniques have shown promise in mitigating distributional discrepancies between datasets, current pseudo-labeling strategies remain vulnerable to background noise, impeding optimal target dataset performance. Additionally, …
-
A comparison of two frequency domain adaptive beamforming algorithms for sonar signal processing
Computer simulation studies of two frequency domain adaptive beamforming algorithms are presented. The two algorithms are the frequency domain adaptive beamforming modified least-mean-square algorithm, and the proposed new frequency domain adaptive beamforming algorithm based on modified adaptive …
-
Bridging Domain Gaps for Cross-Spectrum and Long-range Face Recognition Using Domain Adaptive Machine Learning
… with images fromdifferent modalities or domains( such as infrared to visible, long range to close range,nighttime to daytime, profile to f rontal, e tc.) Additionally, advancements in camerasensors, analytics beyond the visible spectrum, and the increasing size of cross-modaldatasets have …
-
DEEP LEARNING IN MEDICAL IMAGE ANALYSIS: BRAIN STRUCTURAL SEGMENTATION, DIFFUSION MRI RECONSTRUCTION AND DOMAIN ADAPTIVE URINARY TRACT SEGMENTATION
… I proposed CycleFormer, a novel cross-modality domain adaptation method that enhances urinary tract segmentation. Utilizing CT urograms, CycleFormer effectively improves the segmentation performance on non-contrast CT scans, specifically for ureters, and has shown notable improvement over …
Page 1 of 4