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 21 for “"self-supervised deep learning"”.
-
Anomaly Detection for Radio Frequency Signals using Self-Supervised Deep Learning
… warfare applications. In recent years, deep learning (DL) has shown promising results for the problem of RF anomaly detection; however, most of the work in the field assumes a priori knowledge about the data and that is not always practical. Labeling data can be time-consuming and …
-
An investigation into locating generalised articulated pose models using self-supervised deep learning
This thesis investigates how self-supervised learning can be used to locate generalised three-dimensional articulated poses from images. We split this difficult problem into its constituent components, self-supervised keypoint detection to find two-dimensional keypoints from images, and …
-
Unsupervised and Self-Supervised Deep Learning for Seismic Data Processing: Methods and Applications
… across noise types and acquisition geometries. Supervised deep learning requires clean labels, which are rarely available in practice. This thesis develops self-supervised and unsupervised learning frameworks that eliminate the need for clean data and exploit the intrinsic structure of seismic …
-
Supervised and self-supervised deep learning approaches for weed identification and soybean yield prediction
… emphasizing the utilization of advanced supervised and self-supervised deep learning approaches for an innovative solution to weed detection and crop yield prediction. The study focuses on key weed species: Italian ryegrass in wheat, Palmer amaranth, and common ragweed in soybean, which …
-
Methods for tumour aggression prediction in colorectal cancer through virtual immunohistochemistry, supervised, and self-supervised deep learning
… populations of buds in one cohort. Finally, self-supervised learning was employed to train a feature extraction network using the VICReg architecture. The encoded representations were clustered, and the model’s success was determined by running Cox regression on the observed probability …
-
Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback
… of society. This thesis proposes a novel self-supervised deep learning framework CAAD for anomaly detection in wireless communication systems. Specifically, CAAD employs powerful adversarial learning and contrastive learning techniques to learn effective representations of normal and …
-
Unsupervised machine learning for hypothesis discovery and representation learning in biological image and sequence analysis
… show how representations can be combined with unsupervised clustering to discover new functions of proteins from an integrative study of almost 400,000 microscopy images of yeast cells. I will describe new computational methods that reduce barriers in effort and expertise in converting images and …
-
Direct estimation of forest aboveground biomass from UAV LiDAR and RGB observations in forest stands with various tree densities
… manually delineated crowns. Here, we introduce a deep learning approach for crown delineation and AGB estimation reproducible for complex forest structures without relying on hand annotations for training. Firstly, we detect treetop and delineate crowns with LiDAR point cloud using …
-
Pushing the limits of SNR and resolution for in vivo neural imaging via self-supervised learning
… high SNR measurements which makes traditional supervised deep learning not applicable. In this dissertation, I present two generations of self-supervised deep learning frameworks for two-photon voltage imaging denoising (DeepVID) in low-photon regimes, which model noise distributions directly …
-
Novel Computational Methods for Scalable C. elegans Neuroimaging Analysis
… tools, leveraging computer vision and machine learning, to overcome these specific limitations in C. elegans fluorescence neuroimaging. First, to address the challenge of quantifying synaptic structures at scale, I developed WormPsyQi, an automated pipeline using machine learning for robust, …
-
Self-supervised pose estimation
… this thesis, we explore developing and adapting self-supervised deep learning methods for both 2D and 3D pose estimation. Our focus is on creating methods that require minimal or no annotated data for training. This approach provides flexibility in the resulting methods, allowing these to work …
-
Deep Learning-based Hybrid Beamforming, Channel Estimation, and Sparse Signal Recovery for Massive MIMO Systems
… frequency space (OTFS) schemes. In this thesis, deep neural networks (DNNs) are employed to improve the performance of 6G systems. Specifically, three research areas are studied: 1) hybrid analog and digital beamforming based on analytical phase optimization and self-supervised deep learning (DL) …
-
Self-Supervised Learning for Accelerated Magnetic Resonance Imaging
… disrupting clinical workflows. Recently, deep learning methods have gained rapid growth because of their significant performance improvement and real-time reconstruction. Most of existing deep-learning based approaches in MRI reconstruction are in supervised manner, which requires huge …
-
Improving and Integrating Quantitative Single Cell Spatial Biology for Theranostic Medicine
… algorithm (DIMR) for outlier pixel removal and a self-supervised deep learning algorithm for shot noise image filtering (DeepSNiF). Furthermore, we introduce an interpretable spatial cell learning framework called InterSTELLAR, which classifies tissues into distinct clinical types. InterSTELLAR …
-
Improving and Integrating Quantitative Single Cell Spatial Biology for Theranostic Medicine
… algorithm (DIMR) for outlier pixel removal and a self-supervised deep learning algorithm for shot noise image filtering (DeepSNiF). Furthermore, we introduce an interpretable spatial cell learning framework called InterSTELLAR, which classifies tissues into distinct clinical types. InterSTELLAR …
-
Deep Graph Representation Learning and its Application on Graph Clustering
… networks are everywhere in the real world. Deep Graph Representation Learning (DGL) is essential for most graph applications, such as Graph Classification, Link Prediction, and Community Detection. DGL has made significant progress in recent years because of the development of Graph Neural …
-
Advancing deep learning in computational mechanics and biomechanics: overcoming challenges and paving a promising future
Deep learning has revolutionized numerous scientific fields, yet its integration within computational mechanics and biomechanics remains limited. This is primarily due to unique challenges including but not limited to the scarcity of suitable benchmark datasets, uncertainties regarding model …
-
Learning Robust and Interpretable Representations of Spatial Point Processes
… we develop novel statistical and machine learning approaches for robust and interpretable analysis of spatial point patterns. In many applications, spatial patterns are not only shaped by interactions between objects but also by external factors, such as resource availability or spatial …
-
Vision-Based Construction Activity Recognition Using Supervised and Self-Supervised Methods
… recognition methods is their reliance on supervised learning. This approach requires large, labeled datasets for each type of equipment and activity, which can be costly and time-consuming to create. Particularly, for the task of activity recognition and localization that requires …
-
Self-Supervised Physics-Guided Deep Learning for Solving Inverse Problems in Imaging
… amplification and residual artifacts. Recently, deep learning has emerged as an alternative approach for accelerated MRI. Among deep learning techniques, physics-guided deep learning (PG-DL) has drawn great interest, as it incorporates the known physical forward model into the network …
Page 1 of 2