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 20 for “"Weakly-labeled data"”.
-
Face Recognition from Weakly Labeled Data
… in the media usually requires lots of training data to design robust classifiers, which demands a great amount of human effort for annotation. Alternatively, the weakly labeled data is publicly available, but the labels can be ambiguous or noisy. For instance, names in the caption of a news …
-
Audio classification and event detection based on small-size weakly labeled data
… detection and classification using small-size weakly labeled data. Although audio event detection has been studied for years, the research on this topic using weakly labeled data is limited. Many sources of multimedia data lack detailed annotation and rather have only high-level meta-data …
-
Beyond Nouns and Verbs
… models of objects and action classes using large databases of examples (positive and negative) and machine learning to construct models. Visual inference however involves not only detecting and recognizing objects and actions but also extracting rich relationships between objects and actions to …
-
Reducing Human Labor Cost in Deep Learning for Natural Language Processing
… techniques relies on huge amounts of manually labeled data in many applications. However, large amounts of labeled data are usually prohibitive or expensive to obtain. In addition, accurately evaluating the NLP models also requires expansive human evaluation. This dissertation focuses on …
-
Multiscale conditional random fields for machine vision
… Toussaint. We show how to train this model in a weakly-supervised fashion, in which some of the images only have captions specifying which objects are present; this information is propagated down the tree and thus provides weakly labeled data at the leaves, which can be used to improve the …
-
Learning Explainable Facial Features from Noisy Unconstrained Visual Data
… problem, a lack of publicly available data is a major challenge. As with many problems in computer vision, a large portion of facial attribute research is dedicated to improving performance on benchmark datasets. However, it has been shown that research progress on a benchmark dataset …
-
Characterizing the relationship in social media between language and perspective on science-based reasoning as justification for belief
… part of this thesis, a set a Twitter users was labeled as being either "pro-science" (i.e. as having the view that beliefs are rational if and only if they are in accord with science-based reasoning) or "non-pro-science" (i.e. as having the view that beliefs may be reasonable even if they are …
-
Characterizing acoustic environments with OLAF and ELSA
… support for research and creation of labeled data corpora. For instance, the expertise, computational resources, and quantities of data required for deep learning create a significant barrier to its implementation in many fields that it might otherwise impact. The focus of this work is …
-
SINGLE IMAGE BASED CROWD COUNTING USING DEEP LEARNING
… and evaluations on several crowd counting datasets, we demonstrate that the proposed networks achieve significant improvements over existing approaches. We also recognize the need for large amounts of data for training the deep networks and their inability to generalize to new scenes and …
-
Generative Models as Foundation Models for Computer Vision
… [4]–[6]. A key factor in this success is dataset curation, as deep networks are notoriously data-hungry—better datasets often lead to better performance. However, large-scale datasets are both costly and time-consuming to produce. For instance, human annotators frequently spend 20-30 …
-
Visual Saliency Detection and Semantic Segmentation
… is the ability to select the most relevant data in the scene and reduce the amount of data that needs to be processed. We propose a novel unsupervised approach to detect visual saliency in videos. For this, we employ a hierarchical segmentation technique to obtain supervoxels of a video, and …
-
Exploring Strength in Weakness: Multifaceted Weakly Supervised Learning Approaches for Telehealth and Industrial Quality Predictions
The rapid advancement in data collection technologies has significantly impacted the fields of telehealth and industrial manufacturing. However, the challenge of obtaining comprehensive and precise labels for this data poses significant difficulties for traditional machine learning models. This …
-
Learning with Single View Co-training and Marginalized Dropout
… 1) a sufficiently large quantity of training data is available; 2) the training and testing data come from some common distribution. Although these assumptions are often met in practice, there are also many scenarios in which training data from the relevant distribution is insufficient. We …
-
A Machine Learning Framework for Oncological Margin Detection
… time consuming and sensitive nature of the data collection that limits the size and quality of the datasets. We propose to use machine learning techniques to create robust and generalizable cancer recognition models for the iKnife. To do so, we first perform a feasibility study using an …
-
Deep Weakly Supervised Learning for Whole Slide Image Representation: A Multimodal Approach
… deep models necessitates massive amounts of data that must be manually labeled by domain experts. Hand-labeled datasets take time and resources to create, especially when specialized knowledge is required, as in medicine. As a result, practitioners are increasingly focusing on techniques that …
-
Weakly Supervised Learning for Musical Instrument Classification
… models also increase the need for high quality labeled data. For the MIC task, there do not exist such large-scale fully annotated datasets. Instead researchers tend to utilize multi-track data to obtain fine-grained instrument activity annotation. Such datasets are also known as strongly …
-
Learning from text and images: generative and discriminative models for partially labeled data
… It has a variety of applications in multi-media data-mining and computer vision. Traditional machine learning approaches to image annotation require large amounts of labeled data. This requirement is often unrealistic, as obtaining labeled data is, in general, expensive and time consuming. …
-
Reducing the effort for data annotation
… fueled by the increasing availability of large datasets with high-quality annotations. However, the availability of such annotations, also referred to as labels, remains a critical bottleneck for many machine learning applications as they are a prerequisite for supervised model training. This is …
-
Modeling Structured Data with Invertible Generative Models
Data is complex and has a variety of structures and formats. Modeling datasets is a core problem in modern artificial intelligence. Generative models are machine learning models, which model datasets with probability distributions. Deep generative models combine deep learning with probability …
-
Deep regression models for spatio-temporal expression recognition in videos
… learning (DL) models demand a huge amount of data with annotations, which requires a lot of human support with domain expertise. Therefore, leveraging DL models for the regression of expressions with limited annotations remains to be a major bottleneck. Although audio-visual fusion is expected …