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 107 for “"Self-Supervision"”.
-
Visual Intelligence Through Self-Supervision
… human visual systems. This dissertation explores self-supervised learning as a promising approach to overcome these limitations, investigating how machines can learn rich, meaningful representations from visual data without explicit labels, mirroring human visual learning through experience. We …
-
Learning with multimodal self-supervision
… Specifically, we do so by either adapting self-supervised methods to automatically correct freely obtained data labels, or by completely abandoning the use of human labels and instead utilizing the natural co-occurrence of audio and visual information to learn object representations in …
-
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
-
Self-Supervision Initialization for Semantic Segmentation Networks
… does notrely on human generated annotations is self-supervised learning in which annotation scan be computer generated using tasks that force learning image representations such as predicting the rotation of an image. In this thesis, self-supervised methods are evaluated specifically to improve …
-
Multimodal Representation Learning Using Self-Supervision and Attention
… A method to obtain rich joint representations is self-supervised learning, which leverages the underlying structure in the modalities and obtains supervisory signals from the data itself. This is especially helpful to extract generic features hidden in multiple data modalities of biomedical domain …
-
Side information, robustness, and self supervision in imitation learning
Imitation learning refers to a family of learning algorithms enabling the learning agents to learn directly from demonstrations provided by experts, practitioners, and users. While imitation learning methods have been successfully applied to many robot learning and autonomous driving problems, …
-
Self-supervision through Random Segments with Autoregressive Coding (RandSAC)
Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this thesis, we explore the effect various design choices have on the success of …
-
Model-Based Self-Supervision for Fine-Grained Image Understanding
In order to enable robots that perform tasks capably, efficiently, and safely in dynamic environments, we'll need vision systems that are adaptable and can reliably provide detailed and accurate information about the world around the robot. Generative model-based methods are well suited to these …
-
Leveraging domain knowledge for self-supervision in scalable robot learning
… application of robotics in the real world. From self-driving cars to drones and warehouse applications, deep learning has become an integral tool in deploying robots into complex domains. Despite many advances in training efficiency, operating performance, and inference speeds, there is one key …
-
Exploring and Exploiting Structure and Self-supervision in Sequence Learning
… In this thesis, I will study both supervised and self-supervised sequence learning using deep models. Conventional methods for supervised sequence learning are typically designed to study sequences of scalar values or vectors, and are not suitable for structured data such as graphs. I will …
-
3D human pose estimation with self-supervision and learnable data generation
… calibrated multi-view images. We propose a weak supervision approach that combines classical triangulation methods with a multi-view network to generate pseudo-ground-truth 3D images, demonstrating superior results without requiring camera calibration. We then investigate the generation of …
-
Automated radiological grading of spinal MRIs via weak and self-supervision
… for manual annotation in medical imaging through self-supervised learning. To this end, we propose a novel method for learning representations of same-subject, differentmodality images pairs, using registration as a pretext task. This method is used to perform 3D spinal segmentation in MRIs using …
-
Egocentric Audio-Visual Understanding using Approaches for Self-Supervision and Counting
… of repetition counting, for which we utilise the self-supervisory features of repetitive videos for both visual and audio modalities.<br/><br/>Audio is an inherent part of the video stream, as well as an important element in human understanding. We begin by exploring the utility of egocentric …
-
Model-based Self-supervision for Dense Face Alignment and 3D Reconstruction
In the field of monocular 3D reconstruction, self-supervision based on differentiable rendering and a statistical 3D model has been proposed to alleviate the need for datasets with ground truth. In theory, this enables training of neural networks only using unannotated images. However, training …
-
Geospatial Understanding of Foundation Models: Self-Supervision, Robustness, and Resource-Constrained Learning
… three complementary axes. First, we develop self-supervised multispectral pretrained models for satellite image classification by adapting BYOL, BarlowTwins, DINO, MoCo, and Simsiam to multispectral inputs, addressing the limited amount of curated satellite datasets relative to ImageNet. …
-
Generalizable Graph AI for Biomedicine: Data-Driven Self-Supervision and Principled Regularization
… Accordingly, I built some of the first graph self-supervised learning (GSSL) frameworks to systematically explore the utilization of rich, unlabeled graph data. This approach has empirically proven successful in learning more generalizable graph representations across different domains. …
-
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
-
Generative and Self-Supervised Learning for Robotics Problems
… In this dissertation, we apply generative and self-supervised learning as a framework to solve robotics-specific problems. Traditionally, supervised learning relies on human-annotated labels as signal for the training process. Generative, self-supervised learning is a promising approach that …
-
Použití self-supervised learning pro rozpoznání sportovních pozic v obraze
… pozic v obrazových datech za pomocí přístupu self-supervised learning pro docílení vyšší úspěšnosti klasifikace s použitím malého množství anotovaných vzorků. Učení za pomocí self-supervision je docíleno snímky stejné scény z různých úhlů ve stejných a různých časech. Konvoluční neuronová síť …
Page 1 of 6