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 28 for “"Self-Supervision"”.
-
Sample-efficient learning with self-supervision
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-04-12 without embargo terms
-
Large Language Models for Reasoning: From Indirect Supervision to Self-supervision
… of LLMs by shifting from traditional indirect supervision methods to more autonomous self-supervision paradigms. The first part of this dissertation presents two published works that illustrate how task-specific training with indirect supervision improves LLMs’ reasoning ability on …
-
Self-supervision strategies for post-ASR error correction in clinical domain.
… were identified. The study also introduces self-supervision strategies and an edit distance operations-based noising algorithm to optimise error correction processes based on error distributions. The contributions of this research include the creation of a domain-specific ASR dataset …
-
Speech classification and lexical semantic modeling via self-supervision and knowledge transfer
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Cost effectiveness of community-based (DOT) and self-supervised treatment of tuberculosis in Maracha Arua, Uganda
… of DOT however varies with its method of supervision. This study evaluated the cost-effectiveness of community-based and self-supervision strategies of DOT in Maracha, Arua District, Uganda. Patients', community's and health system's costs were obtained through interviews and expenditure …
-
Self-Supervised Learning for Geometry
… capabilities in robots, namely Geometry Self-supervision. With the geometry self-supervision, we allow robots to learn and infer the 3D structure of the scene and ego-motion by watching videos, instead of expensive ground-truth annotation in traditional supervised learning problems. …
-
Optimizing relational search with embedded neural network
… pipeline. The classifier is trained with self-supervision. It learns to optimize the partitioned indexes access pattern to accelerate query performance. Using textual features of user queries, the classifier infers the index access pattern so that fuzzy string matching subqueries are …
-
"Towards Closed-Loop Sleep Monitoring in Parkinson’s Disease: Self-Supervised Learning Strategies for Sleep Stage Classification"
… generalization, this work introduces a self-supervised transformer framework. The model employs a masked autoencoder strategy, pretrained on large public EEG/ECoG datasets from healthy subjects to learn balanced representations of all sleep stages, thereby improving discrimination of …
-
Learning without Labels - Reducing Supervision in Training, Inference, and Evaluation of Deep Neural Networks
This thesis investigates how the reliance on supervision can be reduced across the entire deep learning pipeline. In the training phase, we explore unsupervised fine-tuning, focusing on Source-Free Unsupervised Domain Adaptation scenarios in visual tasks such as Facial Expression Recognition and …
-
Dense visual learning for robot manipulation
… In this thesis we present work that leverages self-supervision, particularly via a mix of geometrical computer vision, deep visual learning, and robotic systems, to scalably produce dense visual inferences of the world state. These methods either enable robots to teach themselves dense visual …
-
Learning-Based Complex Terrain Navigation Under Uncertainty
… learn terrain properties directly from data via self-supervision to automatically penalize trajectories moving through undesirable terrain. However, challenges remain in properly quantifying and mitigating risk due to uncertainty in learned models and improving model generalization in novel …
-
Developing a User-Friendly and Modular Framework for Deep Learning Methods in 3D Bioimage Segmentation
… the latest deep learning innovations, such as self-supervised methods. Self-supervision aims at tackling the important need for deep learning methods in manual annotations by pretraining models on large unannotated datasets to extract information first before retraining them on annotated …
-
Deformable Object Manipulation with a Tactile Reactive Gripper
… configuration spaces, frequent self-occlusion, and high model uncertainty, making global state estimation and predictive modeling unreliable. To address these challenges, we propose a perception-driven framework that combines global visual understanding with local tactile …
-
Deep learning with very few and no labels
… where the network is learned based on self-supervision information across images instead of within one single image. The second one is spatial assembly networks for image representation learning. We introduce a new learnable module, called spatial assembly network (SAN), which performs …
-
Health and safety management in the public sector
… reveals the inescapable requirement to embrace self-supervision in the overarching needs of the host PSO where the health and safety management-of-change process took place. This context statement seeks to scrutinise the line management principles of control, co-operation, communication and …
-
3D Object Detection for Road Safety at Urban Intersections
… to road safety researchers. Mymethod usesweak supervision to fine-tune models trained on autonomous vehicle datasets for traffic observation cameras, achieving high-accuracy localisation. However, this work has the limitation of requiring multi-view data. To solve this, I make a further …
-
Robots as Minions, Sidekicks, and Apprentices: Using Wearable Muscle, Brain, and Motion Sensors for Plug-and-Play Human-Robot Interaction
… behaviors, an apprenticeship framework augments self-supervision with intermittent demonstrations. Systems use and evaluate these algorithms with three interaction paradigms. Subjects supervise and teleoperate robot minions that perform object selection or navigation in mock safety-critical or …
-
Machine learning to model health with multimodal mobile sensor data
… fusion for improved population subtyping, and self-supervision for learning generalized representations. We apply our proposed methods to challenging real-world tasks of predicting mental health and cardio-respiratory fitness through sensor data. First, we study the relationship of passive data …
-
Unifying cross-modal concepts in vision and language
… of concepts across modalities without strong supervision or large amounts of data external to the target task. In visual question answering, models tend to rely on contextual cues or learned priors instead of actually recognizing and linking concepts across modalities. Consequently, when a …
-
Natural Language Foundation Models in Medical Artificial Intelligence
… the potential protective effects of text self-supervision. Next, we explore how conformal prediction can be used to control zero-shot classification performance and preempt compatible inputs for these CLIP-style models. In chapter 4, I describe the development of Articulate Medical …
Page 1 of 2