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 142 for “"Weak Supervision"”.
-
Localizing Objects with Weak Supervision
… To overcome this challenge, several alternative weak labels such as class labels, audio waves, and text captions, can be utilized. These weak labels are either simple to gather from sources like the internet or specialized equipment, or they are less costly to annotate. In this thesis, our aim is …
-
Information extraction with weak supervision
… explores the development and application of weak supervision techniques to address key challenges in three fundamental information extraction (IE) tasks: Named Entity Recognition (NER), Relation Extraction (RE), and Entity Linking (EL). Traditional supervised learning methods in these domains …
-
Strengthening weak supervision for information retrieval
The limited availability of ground truth relevance labels has been a major impediment to the application of supervised machine learning techniques to ad-hoc document retrieval and ranking. As a result, unsupervised scoring methods, such as BM25 and TF-IDF, remain strong competitors to deep learning …
-
Volumetric Weak Supervision for Semantic Segmentation
… of images. To reduce user annotation efforts, weak supervision for semantic segmentation is becoming an area of increasing interest. Weak supervision can take many forms: bounding boxes, scribbles, image level labels. Image level supervision is the least annotation demanding, as the user is …
-
Learning Object Detection with Weak Supervision
… for reducing costs is to train models with weak supervision, which provides a good trade-off between model performance and annotation efficiency. This thesis dedicates to weakly supervised learning in two object-centered application scenarios, i.e., general object detection and RGB-D salient …
-
Learning Structured Models with Weak Supervision
… to these challenges, our study delves into weakly supervised learning, a scenario characterized by training data that may be incomplete, noisy, or imprecisely labeled. Our approach broadly considers any random variable with a correlation to the target label as a source of weak supervision …
-
Learning with Constraint-Based Weak Supervision
… several alternatives to supervised learning. Weak supervision is one such alternative. Weak supervision or weakly supervised learning involves using noisy labels (weak signals of the data) from multiple sources to train machine learning systems. A weak supervision model aggregates multiple …
-
Object Recognition and Parsing with Weak Supervision
… focus on object recognition and parsing with weak supervision, which tackles the problem when only a limited amount of data or label are available for training deep neural networks in the target domain. The goal is to design more advanced computer vision models with enhanced data efficiency …
-
SPARSITY AND WEAK SUPERVISION IN QUANTUM MACHINE LEARNING
Quantum computing is an interdisciplinary field at the intersection of computer science, mathematics, and physics that studies information processing tasks on a quantum computer. A quantum computer is a device whose operations are governed by the laws of quantum mechanics. As building quantum …
-
Interactive Learning of Relation Extractors with Weak Supervision
… some of which use more accurate models of weak supervision from a database. Specifically, this dissertation presents (1) a weakly supervised technique based on multi-instance learning wich allows relations to overlap, (2) a weakly supervised technique that allows learning from only a few …
-
Learning with Weak Supervision for Land Cover Mapping Problems
… that only rely on exact labeled data (strong supervision) have limited performance. This thesis investigates the use of weak supervision to mitigate the problem of not having sufficient samples with exact labels. In a weakly-supervised learning scenario, you have very few training samples that …
-
Harnessing Weak Supervision for Reliable and Scalable Data Annotation
… model development and deployment. Programmatic weak supervision (PWS) offers a promising solution by enabling automatic data labeling through labeling functions (LFs), but faces significant challenges in practical applications. This thesis presents a comprehensive framework to enhance the …
-
Finding Headache Moments from YouTube Videos Using Weak Supervision
… many machine learning systems use some form of weak supervision. The present study aims to use multiple weak supervision sources such as a pretrained deep learning model and several handcrafted heuristic rules; integrate and model them using Snorkel [1] which helps to programmatically build …
-
Context-Aware Message-Level Rumour Detection with Weak Supervision
… on researching ERD on social media by exploiting weak supervision and contextual information. Weak supervision is a branch of ML where noisy and less precise sources (e.g. data patterns) are leveraged to learn limited high-quality labelled data (Ratner et al., 2017). This is intended to reduce the …
-
Conditioning-guided constraint design for reliable learning under weak supervision
… and inference pipelines operate under \emph{weak supervision}: instead of dense ground-truth labels, they rely on partial observations and a collection of \emph{consistency constraints} (e.g., cycle consistency, path consistency, temporal consistency, or rendering-based constraints). A …
-
Posterior Regularization for Learning with Side Information and Weak Supervision
… an IID training corpus. A key challenge for weakly supervised learning is then how to incorporate such kinds of auxiliary information arising from indirect supervision. In this thesis, we present Posterior Regularization, a probabilistic framework for structured, weakly supervised learning. …
-
Inspecting the Machine Learning Pipeline: from Weak Supervision to Explainability
… a framework for inspecting and categorising<br/>weak supervision settings. It can be used for understanding the flexibility and implications of<br/>deciding on an annotation process, for describing a dataset, or for deciding on suitable machine learning<br/>algorithms. In Chapters 3 and 4 we …
-
Learning from Multi-Source Weak Supervision for Neural Text Classification
… but only easy-to-provide heuristic rules as weak supervision. This problem is challenging because rule-induced weak labels are often noisy and incomplete. To address these challenges, we propose a model that can be learned from multiple weak supervision sources with two key components. The …
-
Entity Analysis with Weak Supervision: Typing, Linking, and Attribute Extraction
With the advent of the Web, textual information has grown at an explosive rate. To digest this enormous amount of data, an automatic solution, Information Extraction (IE), has become necessary. Information extraction is a task of converting unstructured text strings into structured machine-readable …
Page 1 of 8