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 52 for “"Label-Efficient"”.

  1. LABEL EFFICIENT LEARNING BEYOND MANUAL ANNOTATIONS

    … vision tasks. However, enormous amount of labeled data is required for supervised learning to achieve good generalization performance. Curating such large-scale datasets is extremely expensive, labor-intensive, and time-consuming. Furthermore, certain domains such as medical imaging are …

    nus Repository record for LABEL EFFICIENT LEARNING BEYOND MANUAL ANNOTATIONS (opens in a new tab) Download file for LABEL EFFICIENT LEARNING BEYOND MANUAL ANNOTATIONS (opens in a new tab)

  2. Label-Efficient Learning For Scene Segmentation

    … This thesis addresses this critical challenge of label scarcity in training object segmentation models, a task often hindered by the need for extensive and costly manual annotation. Our research explores two complementary strategies towards improving label efficiency for training deep models: …

    anu Repository record for Label-Efficient Learning For Scene Segmentation (opens in a new tab)

  3. Label-Efficient Segmentation for Diverse Scenarios

    … In this thesis, we analyze the importance label-efficient segmentation techniques and provide a series of methods to address segmentation tasks in different scenarios. First, we propose a Deep Reasoning Network for few-shot semantic segmentation, termed as DRNet, which is a novel approach …

    adelaide Repository record for Label-Efficient Segmentation for Diverse Scenarios (opens in a new tab)

  4. Label Efficient Learning for Semantic Segmentation

    … as ’data-hungry’, requiring vast quantities of labelled data to ensure effective generalisation across a variety of real-world scenarios. The process of data annotation, integral to these methods, is both resource-intensive and time-consuming. This challenge is particularly pronounced in the …

    adelaide Repository record for Label Efficient Learning for Semantic Segmentation (opens in a new tab)

  5. Label-efficient learning for medical images

    … and neurovascular bundle, with insufficient labels. Furthermore, generalisation failure has been widely acknowledged due to the limited training samples and their high variability, making domain shifts between training and application data common.</p> <p>This thesis proposes approaches to …

    oxford Repository record for Label-efficient learning for medical images (opens in a new tab)

  6. Label-Efficient Visual Understanding with Consistency Constraints

    … tasks, as long as a sufficiently large labeled dataset is available during the training time. However, the progress of these visual tasks is limited by the number of manual annotations. On the other hand, it is usually time-consuming and error-prone to annotate visual data, rendering the …

    vt Repository record for Label-Efficient Visual Understanding with Consistency Constraints (opens in a new tab)

  7. Label-efficient learning paradigms for scalable robot perception

    … sparse and weak supervision, and culminating in label-free domain adaptation. In doing so, this thesis develops perception approaches that minimize the reliance on dense annotations while improving scalability and adaptability for large-scale real-world deployment. <br><br>The first part of this …

    freiburg-diss Repository record for Label-efficient learning paradigms for scalable robot perception (opens in a new tab)

  8. Towards Label-Efficient Approaches For Dense Video Tasks

    … beyond closed-world settings. Spatio-temporal labeling is costly, while real-world applications demand models that interpret novel, open-ended queries. This dissertation develops methods to improve label efficiency and enable flexible, open-world video analysis. To alleviate the annotation …

    ucf Repository record for Towards Label-Efficient Approaches For Dense Video Tasks (opens in a new tab)

  9. TOWARDS LABEL-EFFICIENT DEEP LEARNING ON GRAPH-STRUCTURED DATA

    … be quite difficult. In this thesis, we develop label-efficient DL methods that achieve superior performance with a few labels. First, we build very deep graph neural networks that can capture rich semantic information from unlabeled data. Second, we propose two novel active learning strategies …

    nus Repository record for TOWARDS LABEL-EFFICIENT DEEP LEARNING ON GRAPH-STRUCTURED DATA (opens in a new tab) Download file for TOWARDS LABEL-EFFICIENT DEEP LEARNING ON GRAPH-STRUCTURED DATA (opens in a new tab)

  10. LABEL-EFFICIENT LEARNING: BUILDING AI MODELS WITH LIMITED DATA

    … relies on large-scale datasets with high-quality labels, which are expensive and time-consuming to acquire. In many real-world scenarios only limited labeled data is available, which is insufficient for training well-generalized models. This thesis advances label-efficient learning by exploiting …

    nus Repository record for LABEL-EFFICIENT LEARNING: BUILDING AI MODELS WITH LIMITED DATA (opens in a new tab) Download file for LABEL-EFFICIENT LEARNING: BUILDING AI MODELS WITH LIMITED DATA (opens in a new tab)

  11. Towards label-efficient deep learning for medical image analysis

    … time-consuming collection of large quantities of labeled data, which is not always available. This dissertation investigates the use of self-supervised and generative methods to enhance the label efficiency of deep learning models for 3D medical image analysis. Unlike natural images, medical …

    bu Repository record for Towards label-efficient deep learning for medical image analysis (opens in a new tab)

  12. Deep domain adaptation for label-efficient and generalizable bearing fault diagnosis

    … domain adaptation is a type of data-centric, label-efficient transfer learning approach based on deep neural network construction. Bearing fault diagnosis is a field which aims to perform analysis on the vibration signals generated from bearing apparatus. Different types of model structure and …

    texas Repository record for Deep domain adaptation for label-efficient and generalizable bearing fault diagnosis (opens in a new tab)

  13. Towards Scalable and Label-Efficient Visual Perception with Vision Foundation Models

    … they rely heavily on dense supervision, fixed label spaces, and modality-specific assumptions, limiting their applicability in open, dynamic, and resource-constrained settings. This dissertation addresses these limitations by developing scalable and label-efficient perception frameworks that …

    jhu Repository record for Towards Scalable and Label-Efficient Visual Perception with Vision Foundation Models (opens in a new tab)

  14. Modelling Human Behaviour in Smart Buildings Through Explainable Label-Efficient Learning Methods

    … a central role in enabling data-driven, energy efficient control strategies that enhance sustainability while maintaining comfort. However, existing approaches often rely on large, labeled datasets collected from a single environment. When deployed in new settings, their performance degrades due …

    concordia Download PDF for Modelling Human Behaviour in Smart Buildings Through Explainable Label-Efficient Learning Methods (opens in a new tab)

  15. Enhancing Microsleep Prediction Performance Through Temporal Modeling, Multimodal Fusion, and Label-Efficient Learning

    … forecasting, multimodal EEG–EOG integration, and label-efficient learning. The findings show that physiologically meaningful EEG features provide informative and discriminative representations for microsleep prediction, while temporal modelling substantially improves forecasting performance by …

    dcu Download PDF for Enhancing Microsleep Prediction Performance Through Temporal Modeling, Multimodal Fusion, and Label-Efficient Learning (opens in a new tab)

  16. Deep Learning for 3D Point Clouds: Multimodal and Label-Efficient Learning for Geoscience Applications

    … develops a series of multimodal and data-efficient deep learning frameworks across diverse geoscientific contexts. Current approaches to multimodal fusion often convert 3D point clouds into 2D rasters and stack them with corresponding spectral images. While this strategy is practical and …

    fu-berlin Repository record for Deep Learning for 3D Point Clouds: Multimodal and Label-Efficient Learning for Geoscience Applications (opens in a new tab)

  17. Label Efficient Learning for Medical Image Segmentation over Partially Labeled Dataset: Towards a Single, Unified and Lifelong Whole-body Organ Segmentation Model

    … large amounts of medical images with fully labeled masks. However, annotating organs and lesions is both costly and time-consuming, and also requires domain expertise and clinical experience, which make it very difficult to collect a fully labeled dataset with large sample size. Therefore, …

    buffalo Repository record for Label Efficient Learning for Medical Image Segmentation over Partially Labeled Dataset: Towards a Single, Unified and Lifelong Whole-body Organ Segmentation Model (opens in a new tab)

  18. Modeling Single-Cell Data: Recursive Clustering for Resolving Cellular Heterogeneity in scRNA-seq and Label-Efficient Deep Learning for Subcellular Protein Localization in Fluorescence Microscopy

    … microscopy, this dissertation develops two label-efficient approaches for single-cell subcellular protein localization. The first adapts self-supervised learning to microscopy using tailored image augmentations and signal-aware crop and mask sampling that preserve sparse protein localization …

    gatech Repository record for Modeling Single-Cell Data: Recursive Clustering for Resolving Cellular Heterogeneity in scRNA-seq and Label-Efficient Deep Learning for Subcellular Protein Localization in Fluorescence Microscopy (opens in a new tab)

Page 1 of 3