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 906 for “"self-supervised"”.
-
Self-Supervised Spoofing Detection
… cost, or reliance on predefined thresholds. Supervised machine learning models, while powerful, require large labeled datasets and struggle to generalize to unseen spoofing scenarios. In this work, we propose a self-supervised spoofing detection framework based on Adaptive Sparse Gaussian …
-
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 …
-
Self-supervised pose estimation
… this 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 …
-
Self-Supervised Learning for Geometry
… deep learning problems. Differ from conventional supervised learning methods that using expensive annotations as the supervisory signal, we advocate for the use of geometry as a supervisory signal to improve the perceptual capabilities in robots, namely Geometry Self-supervision. With the geometry …
-
Self-supervised video representation learning
… strong video representations efficiently via self-supervised learning: a method that learns from the data rather than human annotations.</p> <p>The thesis is structured around three themes: (1) self-supervised learning for short-term videos, (2) efficient video representation learning, and (3) …
-
Self-Supervised & Explanation Based Handwriting Verification
… documents typically employ neural network-based supervised learning approaches. These methods heavily rely on labeled datasets where each handwriting sample is attributed to a specific writer. During training phase, the model learns to differentiate and classify handwritten documents based on …
-
Information dynamics of self supervised learning
Self-supervised learning (SSL) refers to a family of training strategies that allow task-agnostic representation learning across multifarious data modalities. This ability of SSL algorithms to overcome the need for task-specific empirical risk minimization is key for the construction of …
-
Self-supervised multi-contrast MRI denoising
… accuracy. This thesis presents the "Corruption2Self" (C2S) framework, a self-supervised method for multi-contrast MRI denoising. C2S utilizes self-generated pseudo-labels from noisy data to enhance contrast fusion and Signal-to-Noise Ratio (SNR), providing a robust solution that facilitates …
-
Structural Self-Supervised Objectives for Transformers
In this Thesis, we leverage unsupervised raw data to develop more efficient pre-training objectives and self-supervised tasks that align well with downstream applications. In the first part, we present three alternative objectives to BERT’s Masked Language Modeling (MLM), namely Random Token …
-
Phoneme segmentation using self-supervised speech models
… the utility of representations learned in self-supervised pre-training for the task. Our model extends transformer-style encoders with strategically placed convolutions that manipulate features learned in pre-training. Using the TIMIT and Buckeye corpora we train and test the model in the …
-
SELF SUPERVISED LEARNING FOR ACCURATE BIOMARKER PREDICTION
Recent advances in self-supervised learning (SSL) have opened up new possibilities for accurate biomarker prediction, particularly in the scenario where labeled medical data is scarce. This thesis explores the use of SSL approaches to electrocardiogram (ECG) signal representation learning, a common …
-
SELF-SUPERVISED MODELING FOR MULTI-MODAL UNDERSTANDING
… but complementary information. Currently, self-supervised learning has emerged as a promising approach to learn meaningful representations from many modalities separately, including text, speech, and vision. In this thesis, we aim to leverage self-supervised pre-training techniques for …
-
Self-Supervised Monocular Depth Estimation and Beyond
… image, has advanced with deep learning. While self-supervised methods reduce reliance on ground-truth data, supervised techniques currently yield superior performance. This thesis introduces novel contributions to enhance self-supervised monocular depth estimation’s robustness, accuracy, and …
-
Visual Domain Generalization via Self-Supervised Learning
L'abstract è presente nell'allegato / the abstract is in the attachment
-
SELF SUPERVISED LEARNING ON LARGE SCALE DATASETS
… can be taught without using any labels using Self-Supervised Learning (SSL). We show that generally training machines without using any labels can result in less biased and more robust representations. This manuscript deals with mainly four types of issues in SSL. The first problem we tackle …
-
Towards Efficient Self-Supervised Learning on Graphs
… prevailing methods have predominantly focused on supervised learning, resulting in several limitations, such as heavy reliance on labels and subpar generalization. To address the scarcity of labels, self-supervised learning (SSL) has emerged as a promising approach for graph data. Traditional SSL …
Page 1 of 46