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 151 for “"metric learning"”.
-
Sparse distance metric learning
<p>A good distance metric can improve the accuracy of a nearest neighbour classifier. Xing et al. (2002) proposed distance metric learning to find a linear transformation of the data so that observations of different classes are better separated. For high-dimensional problems where many …
-
Metric Learning: A Deep Dive
H Μάθηση Μετρικής είναι ένα σημαντικό πρόβλημα της Μηχανικής Μάθησης. Ο σκοπός της είναι η εκμάθηση μιας μετρικής, η οποία έχει την ιδιότητα να μειώνει την απόσταση μεταξύ όμοιων αντικειμένων και να αυξάνει την απόσταση μεταξύ ανόμοιων. Το τι είναι όμοιο και τι ανόμοιο μπορεί να είναι κάπως …
-
Metric Learning for Hermitian Manifolds
In recent years, manifold learning has emerged as one of the most promising approaches for performing nonparametric dimension reduction. While numerous manifold learning algorithms of varying degrees of complexity have been proposed, these algorithms rarely preserve the intrinsic geometry of the …
-
Automatic target recognition with deep metric learning.
… we propose solutions that are based on Deep Metric Learning (DML). DML is a technique that has been recently proposed to learn a transformation to a representation space (embedding space) in end-to-end manner based on convolutional neural networks. We explore three distinct approaches. The …
-
Online Metric Learning for Multi-Label Classification
… such as online sequential multi-label extreme learning machine (OSML-ELM) and stochastic gradient descent (SGD), have shown a promising performance on multi-label classification. However, these works lack analysis of loss function and do not consider the label dependency. To fill the gap of …
-
Supervised distance metric learning for pattern recognition
… in other modeling disciplines does the distance metric used (a measure for dissimilarity) play an important role in the growing field of machine learning. Often, predefined distance metrics (e.g. the Euclidean one) are used to perform such measurement. Unfortunately, most of them ignore any …
-
Efficient and scalable approaches to Mahalanobis distance metric learning
… of an appropriate data-dependent distance metric is a compelling goal for many visual recognition tasks. This thesis proposes three efficient and scalable distance learning algorithms by employing the principle of margin maximization to secure better generalization performances. The …
-
Learning to Measure: Distance Metric Learning with Structured Sparsity
Many important machine learning and data mining algorithms rely on a measure to provide a notion of distance or dissimilarity. Naive metrics such as the Euclidean distance are incapable of leveraging task-specific information, and consider all features as equal. A learned distance metric can become …
-
A scalable metric learning based voting method for expression recognition
… a facial expression classification method using metric learning-based k-nearest neighbor voting. To achieve accurate classification of a facial expression from frontal face images, we first learn a distance metric structure from training data that characterizes the feature space pattern, then use …
-
Vision transformer fine-tuning for image similarity using metric learning /
… tracking. This thesis investigates how different metric learning loss functions affect the finetuning of a DINOv2 Vision Transformer for image similarity tasks. Experiments are conducted on the DISC21 dataset, a largescale benchmark for image copy detection. Five loss functions—contrastive, …
-
Metric learning for incorporating privileged information in prototype-based models
… classification models, and particularly Learning Vector Quantization (LVQ) frameworks with adaptive metrics, are powerful supervised classification techniques with good generalization behaviour. This thesis proposes three advanced learning methodologies, in the context of LVQ, aiming at …
-
Reconstructing Cell Lineage Trees from Phenotypic Features with Metric Learning
… we introduce \emph{CellTreeQM}, a novel deep learning method based on transformer architectures that learns an embedding space with geometric properties optimized for tree-graph inference. By formulating lineage reconstruction as a tree-metric learning problem, we have systematically explored …
-
Metric learning with siamese networks for re-identification and tracking
… for autonomous driving, access control in biometrics, etc. Once a person has been detected, VOT produces continuous bounding boxes for that person over a video sequence given an initial location. At the same time, ReID identifies lost tracks of a person or identifies persons or objects seen in …
-
Weakly supervised metric learning for estimating autonomous vehicle terrain traversability cost
In this thesis, we address the challenge of learning the cost of traversing over arbitrary types of terrain using metric learning with weak labels. To address the challenge of manually labeling data, we construct our dataset by driving a HUSKY unmanned ground vehicle (UGV) throughout the UT Austin …
-
Deep Contrastive Metric Learning to Detect Polymicrogyria in Pediatric Brain MRI
… we propose a novel center-based deep contrastive metric learning loss function (named cDCM Loss) to deal with this difficult problem. Cross-entropy-based loss functions do not lead to models with good generalization on small and imbalanced dataset with partially known distributions. We conduct …
-
Improving Representation Learning for Diverse Modalities and Distributions with Metric Learning
… challenges in computer vision and machine learning. In the case of image modality, convolutional neural networks (CNNs) have been successful in encoding relevant information from data and creating enhanced feature representations. These representations have found applications in various …
-
Vehicle re-identification from multi-modal vision sensors with deep metric learning
… a deep neural framework based on the meta-learning training paradigm. Meta-learning leverages a two-step gradient calculation process that exposes the model to the train-test domain shift during backpropagation. This technique proves to improve out-of-distribution generalisation of the …
Page 1 of 8