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 43 for “"Supervised Contrastive Learning"”.
-
MRI-Based Brain Age Estimation Using Supervised Contrastive Learning
… or clinical utility. This thesis proposes using supervised contrastive learning with Rank-N-Contrast (RNC) loss and Grad-RAM for explainability utilizing structural T1w MRI data. Results indicate that the supervised contrastive strategy significantly outperformed ResNet models, achieving a mean …
-
Benchmarking Self-Supervised Contrastive Learning Methods for Image-based Plant Phenotyping
… image analysis tools. Over the past decade, deep learning has been widely successful for image-based tasks like image classification, object detection, image segmentation and object counting. While deep learning has been applied to image-based plant phenotyping tasks like plant species …
-
Self-Supervised Contrastive Learning Using EEG Signals For Mental Stress Assessment
A study is presented to investigate self-supervised contrastive learning (SSCL) models using physiological data obtained from non-invasive wearable sensors for mental stress assessment. The present work involved acquisition of electroencephalography (EEG) signals using wearable sensors, signal …
-
Discovering Global False Negatives on the Fly for Self-supervised Contrastive Learning
In self-supervised contrastive learning, negative pairs are typically constructed using an anchor image and a sample drawn from the entire dataset, excluding the anchor. However, this approach can result in the creation of negative pairs with similar semantics, referred to as “false negatives”, …
-
A Self-Supervised Contrastive Learning Approach for Whole Slide Image Representation in Digital Pathology
… has changed the field of digital pathology. Deep learning can help pathologists segment and categorize regions and nuclei and search among WSIs for comparable morphology. However, because of the large data size of WSIs, representing digitized pathology slides has proven difficult. Furthermore, the …
-
From Detection to Reliability: Supervised Contrastive Learning and Perception Evaluation in Dynamic Conditions for Autonomous Driving
… side, this work develops representation learning frameworks grounded in Supervised Contrastive Learning (SCL). Applied to the Second Strategic Highway Research Program (SHRP 2) Naturalistic Driving Study (NDS) video data, SCL enhances intra-class cohesion and inter-class separation in the …
-
MSCL-X: Meta Supervised Contrastive Learning with Gaussian Prototypes For Robust Few-Shot Open-Set Modulation Classification
… questions concerning the ability to institute learning frameworks that could perform well on few-shot and open-set conditions. Hence the thesis attempts to address the same by proposing two complementary learning-based frameworks for few-shot open-set modulation recognition by using signal …
-
Contrastive Learning Techniques for Fraud Detection
… malicious user sessions, often using deep learning models, but several challenges hinder effective deployment. Attackers can craft diverse malicious sessions that closely resemble normal ones, complicating the learning of robust decision boundaries. While supervised contrastive learning …
-
Representation learning for OOD detection and explanation
In recent years, the use of machine learning (ML) models, particularly black box neural<br/>networks, has increased in popularity and is deployed in real-life settings for a range of<br/>different tasks. However, ML models can make overconfident and incorrect predictions on<br/>out-of-distribution …
-
LEARNING-BASED METHODS FOR BRAIN LESION ANALYSIS AND MEDICAL IMAGE REGRESSION: TRANSFER LEARNING, WEAK SUPERVISION, AND REPRESENTATION LEARNING
… across cohorts. This thesis proposes three learning-based solutions: (1) a transfer learning strategy using a model pretrained on 14,000 UK Biobank subjects to improve white matter hyperintensity (WMH) segmentation; (2) WMH-DualTasker, a weakly supervised framework that uses visual rating …
-
Rozpoznání výrobce a modelu vozidel
… neuronové sítě, a přístup, kdy za pomocí metody supervised contrastive learning byly embeddingy z enkodérů shlukovány za účelem snazší klasifikace. Jelikož první uvedený přístup vracel přesnější výsledky, byl použit v dalších experimentech. V nich se použilo větší množství obrázků z naší datové …
-
Fusion model using unsupervised and self-supervised learning for lung ultrasound video classification of consolidations
… minimal reliance on labeled datasets. First, unsupervised methods using hand-crafted and deep features were explored for clustering frame-level patterns. Building on the insights of this study, the thesis then contributes a fusion-based framework that combines self-supervised contrastive …
-
DOMAIN-SPECIFIC ADAPTATION AND MULTI-HOP REASONING IN CHEMISTRY AND BIOMEDICINE
… embedding model fine-tuned via self-supervised contrastive learning on an extensive biomedical corpus, which achieves state-of-the-art performance on MedTEB. Third, we develop GraphRAG, an automated pipeline that constructs chemical knowledge graphs from ChemRxiv preprints and …
-
Bridging Across Viewpoints, Domains and Modalities for Video Understanding
… video understanding systems. We first propose a supervised contrastive learning framework that leverages synchronized multi-view videos and a hardness-aware loss to learn viewpoint-invariant action representations. We then extend this to the self-supervised setting with a masked autoencoder that …
-
Self-Supervised Learning Using Physiological Signals from Wearable Sensors for Mental Stress Assessment
This study aims to present a self-supervised contrastive learning (SSCL) model that will detect cognitive stress using physiological signals acquired from non-invasive wearable sensors. This study involved data collection using wearable sensors, feature extraction, normalization, and combination of …
-
Self-Supervised Learning Method for Semantic Segmentation of LiDAR Point Clouds
… LiDAR point clouds, largely the adopting of deep learning techniques. There are the related works of 3D semantic segmentation, including neural network models to process converted voxels, points, and graphs. However, point-based methods are not taken into account local structure feature, resulting …
-
Advancing affect modelling via representation learning
… advancements with the rise of machine learning. However, key challenges still need to be addressed, particularly in learning generalisable affective representations across different modalities and scenarios, especially in contexts where data is scarce or incomplete. This thesis explores …
-
Federated Learning on Knowledge Graphs via Contrastive Alignment
In traditional federated learning (FL) frameworks for knowledge graph embeddings (KGE), individual clients train their local KGE models independently, and a central server collects and aggregates (e.g., by averaging) these models to produce a global one. This process ensures data privacy throughout …
-
A Contrastive Learning Approach for Automated Identification of Anatomical Landmarks in 3D Human Torso Surface Scans
… and subject to operator bias. Using machine learning (ML) algorithms to automate the identification of fiducials would mitigate operator bias and yield reliable, objective measurements. Here, we propose an ML framework to automate the identification of thirteen anatomical landmarks in 3D …
-
Improving language models with novel contrastive learning objectives
Contrastive learning (CL) has recently emerged as an effective technique in natural language processing, especially in the important area of language modeling. In this work, we offer novel methods for deploying CL in both pretraining and finetuning of language models. First, we present PACT …
Page 1 of 3