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 20 for “"Few-Shot Learning (FSL)"”.
-
Few-Shot learning for image-based anomaly detection /
… samples. The aim of this work is to develop a Few-Shot Learning (FSL) extension for the PatchCore model by introducing the proposed DualPatchCore architecture, which incorporates an additional memory bank for storing anomalous feature embeddings. The proposed model is implemented, trained, and …
-
Mokymosi iš nedaug duomenų metodų tyrimas ir jų taikymas marketingo vaizdams vertinti /
This bachelor thesis explores few-shot learning (FSL) methods and their application in predicting the performance of marketing images. The aim is to evaluate whether deep learning techniques, such as transfer learning, prototypical networks, and MAML, can be effective under data-scarce conditions. …
-
Data augmentation as an engine: a multidimensional few-shot analysis
… analysis of data augmentation (DA) in few-shot learning (FSL), investigating the dynamics among augmentation strategies, model architectures, and label granularity. We evaluate four FSL paradigms (Linear Probe, Prototypical Networks, SetFit, and LoRA) across five benchmarks and …
-
Few-shot Learning for NER using MAML
This thesis investigates the application of Few-Shot Learning (FSL) using Model-Agnostic Meta-Learning (MAML) to enhance Named Entity Recognition (NER) within the domain of Natural Language Processing (NLP), specifically focusing on chemical datasets. The primary challenge addressed is the …
-
Advanced trust evaluation and estimation solutions for the internet of things
… a suite of advanced technologies, including Few Shot Learning (FSL), Transfer Learning (TL), Machine Learning (ML), Intrusion Detection System (IDS), Distributed Ledger Technology (DLT), Physical Unclonable Function (PUF), and Trusted Execution Environment (TEE). This approach serves a dual …
-
Comparing human and generative AI annotation performance: Understanding linguistic features of teacher talk in classroom discussions
… train a human annotator and an AI model through few-shot learning (FSL). The AI and human annotators were then tested on their ability to identify the “Connecting Ideas” practice on 30 randomly selected excerpts from classroom discussions and evaluated using precision, recall, accuracy, and …
-
Towards Leveraging Sparse Infrared Datasets for Multiple View Synthesis, Few Shot Learning and Background Invariant Recognition
… dissertation presents a study of various machine learning techniques for recognizing vehicular objects in infrared images. State of the art methods for computer vision have not been widely explored for this part of the electromagnetic spectrum (EM). Challenges that arise due to the dearth of …
-
Few-shot Learning for Medical Image Classification
… datasets. It hinders the application of deep learning methods in medical image field. Few-shot Learning (FSL) is a type of machine learning problem that has only a limited number of training examples with supervised information. It aims to reduce data gathering effort and computational cost. …
-
A deep learning approach for semantic segmentation and its application on CTC.
… a convolutional neural network (CNN)-based deep learning (DL) approach, and a sequential episodic training with dual contrastive learning Approach (G-SET-DCL) that has a flavor of few-shot learning (FSL). To address the challenges of colon segmentation, an MRF-based method integrating image …
-
Face Image and Video Analysis in Biometrics and Health Applications
… disciplines, ranging from computer vision, deep learning, to neuroscience and biometrics. In this work, we analyze the face characteristics from digital images and videos in the areas of morphing attack and defense, and autism diagnosis. For face morphing attacks generation, we proposed a …
-
Solving Visual Species Recognition with Open-World Resources
… management. However, training such a machine learning model typically requires a large amount of species-level annotated data, which is costly in terms of time, budget, and domain expertise. In addition, observations of species naturally follow a long-tailed distribution, where certain rare …
-
Solving Visual Species Recognition with Open-World Resources
… management. However, training such a machine learning model typically requires a large amount of species-level annotated data, which is costly in terms of time, budget, and domain expertise. In addition, observations of species naturally follow a long-tailed distribution, where certain rare …
-
Improving the Human-Machine Interaction of AI Systems for System Health Monitoring
… distinct steps: (1) data collection, (2) a deep learning model, and (3) deployment/usability. The data collection develops a dataset with the highest difference between classes, controlling location and data type. After collection, the data is provided to a few-shot learning (FSL) model. The FSL …
-
Novel Geometric Methods for Deep Learning
… is to demystify the black-box nature of deep learning models and enhance various aspects of DNNs, including uncertainty awareness, data efficiency, learning continuity, and more.(I) Inherent uncertainty during the learning process of DNNs can cast doubts on their predictions. Ensemble …
-
Temporal Aggregation Approaches for Few-shot Human Action Recognition in Videos
Over the past decade, the research of deep learning has dramatically progressed and achieved overwhelming performance for various tasks. This success is highly dependent on a large number of manually labeled data. However, it is not always possible to collect enough training data, meanwhile …
-
Privacy-Preserving and Resource-Aware Intrusion Detection Using Federated Few-Shot Learning
… limitations of centralized processing. Federated Learning (FL) offers a promising alternative by enabling decentralized model training across distributed devices without the need to share data. However, FL alone often struggles due to the limited availability of labeled intrusion data in …
-
Object Recognition and Visual Question Answering with Limited Supervision: From Episodic Learning to Foundational Models
The rapid advancement of deep learning has transformed computer vision, largely driven by the availability of large-scale labeled datasets. However, collecting and annotating sufficient data across diverse domains remains costly and often impractical. Consequently, enabling visual understanding …
-
Discovering Viral Hosts, Mutations, and Diseases using Machine Learning
… virus cause in humans. We propose novel machine learning (ML)-based solutions to these three different problems in computational virology. (i) We develop a viral protein language model for predicting the host infected by a virus, given only the sequence of one of its proteins. Our approach, …
-
Novel Deep Learning Models for Radar-Based Human Activity Recognition
This dissertation presents a comprehensive deep learning pipeline addressing key challenges in radar-based human activity recognition (HAR). Radar-based radio-frequency sensing technology offers distinct advantages such as privacy preservation and robustness to illumination changes. However, its …
-
Deep Learning-Based Intrusion Detection Methods for Computer Networks and Privacy-Preserving Authentication Method for Vehicular Ad Hoc Networks
… academia and industry have turned to machine learning (ML) techniques to develop Intrusion Detection Systems (IDSes) for computer networks. However, many of the datasets use to train ML classifiers for detecting intrusions are not balanced, with some classes having fewer samples than others. …