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 7779 for “"Supervised"”.
-
SUPERVISED AND SELF-SUPERVISED APPROACHES FOR VIDEO UNDERSTANDING
… tasks. We first present an approach for supervised pose-based action recognition with a novel architecture and pose-aware data augmentation strategy. Use of pose instead of RGB helps us better capture motion information and avoid scene and object biases. Next, we investigate …
-
On visual explanation of supervised and self-supervised learning
Τα τελευταία χρόνια, η ταχεία ανάπτυξη των Νευρωνικών Δικτύων Βάθους έχει επιφέρει αξιοσημείωτα επιτεύγματα σε πολλές εργασίες Όρασης Υπολογιστών. Η αυξανόμενη πολυπλοκότητα των μοντέλων, ο μεγάλος όγκος δεδομένων καθώς και η επίβλεψη κατά τη διάρκεια της εκπαίδευσης των μοντέλων είναι οι κύριες …
-
Supervised and Self-Supervised Learning for Accelerated Medical Imaging
… dissertation explores learned reconstruction in supervised and unsupervised settings. We first propose a fully supervised reconstruction method for sparse-view dedicated breast CT, leading to three times radiation dose reduction. Supervised learning typically requires a vast quantity of fully …
-
Scaling Local Learning for Supervised and Self-supervised Learning
… existing local-learning frameworks to self-supervised learning tasks, specifically using the SimCLR method. However, existing local-learning frameworks lack in performance due to task-relevant information collapse in early layers. To address the issue, we propose modifying the local …
-
Beyond Supervised Learning
… breaks with the conventions of the traditional supervised machine learning paradigm that relies on quantitative in-domain evaluation for optimization, performance measurement, and model selection. The dissertation summarizes existing research to build a theoretical foundation for zero-shot …
-
Self-Supervised and Weakly-Supervised Computer Vision Methods for Lensless Imaging
… Therefore, there is a need to develop self-supervised or weakly-supervised CV methods that can operate without detailed annotations. Besides its use in POCT, lensless imaging is an interesting case study as it poses additional challenges to CV including low resolution, potentially large …
-
Detecting Online Hate Speech Using Both Supervised and Weakly-Supervised Approaches
… well kept. Then we propose two types of supervised hate speech detection models that incorporate context information, a logistic regression model with context features and a neural network model with learning components for context. Further, to address various limitations of supervised …
-
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 …
-
Variable selection for supervised and semi-supervised mixtures of contaminated Gaussian distributions
… of contaminated Gaussian distributions in the supervised and semi-supervised learning framework. The performance of this approach in both settings is explored in both simulated and plasmode data. The criterion used to choose variables is based on classification performance. The results show …
-
Few-Shot Medical Image Segmentation Using Semi-Supervised and Weakly-Supervised Learning
… structures: 1- We propose a novel weakly- supervised learning method for the rapid annotation of the left ventricle and based on its circular shape. 2-We introduce a novel physics-informed label-propagation method based on the patient-specific characteristics of the left ventricle to …
-
Enhancing weakly supervised object detection via long-term self-supervised instance mining
… recognise objects within images. However, fully supervised object detection (FSOD) methods re- quire expensive bounding box annotations, which can be time-consuming to compile for large-scale datasets. Weakly Supervised Object Detection (WSOD) presents a promising alternative by utilising only …
-
Kernelized Supervised Dictionary Learning
… the dictionary is mainly computed using unsupervised approaches such as k-means. These approaches learn the dictionary by minimizing the reconstruction error without taking into account the category information, which is not optimal in classification tasks. In this thesis, we propose a …
-
Semi-Supervised Gait Recognition
In this work, we examine semi-supervised learning for Gait recognition with a limited number of labeled samples. Our research focus on two distinct aspects for limited labels, 1)closed-set: with limited labeled samples per individual, and 2) open-set: with limited labeled individuals. We find …
-
Self-supervised video understanding
… and video. There has also been much work done on supervised learning—teaching machines to solve these tasks using human-annotated labels. However, it is insufficient for machines to know only the names and locations of certain objects; many tasks require a deeper understanding of the complex …
-
Distributed Supervised Statistical Learning
… In this thesis, we focus on distributed supervised statistical learning where sparse linear regression analysis is performed in a distributed framework. These methods are frequently applied in a variety of disciplines tackling large scale datasets analysis, including engineering, …
-
Supervised Progressive Geospatial Interlinking
Η Διασύνδεση Γεωχωρικών Δεδομένων αποτελεί μια χρήσιμη διαδικασία, κατά την οποία ζεύγη γεωμετριών συνδέονται σύμφωνα με τις τοπολογικές τους σχέσεις. H διαδικασία αυτή, ωστόσο, έχει υψηλό υπολογιστικό κόστος, το οποίο κλιμακώνεται ελάχιστα σε μεγάλο όγκο δεδομένων. Πρόσφατα προτάθηκαν αλγόριθμοι …
-
Self-supervised pose estimation
… 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 with …
-
Supervised study of English
Abstract not available
-
Weakly-supervised text classification
… many real-world applications. Although many semi-supervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited supervision types. In this work, we propose a weakly-supervised framework that addresses the lack of …
Page 1 of 389