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 72 for “"Limited Supervision"”.

  1. Counting with limited supervision

    … of every object during training to act as supervision.</p> <p>In this thesis, we aim to further automated counting methods with the goal of replicating the human ability to perform completely naive counting. To achieve this, we recognise that counting is composed of, at its heart, two …

    oxford Repository record for Counting with limited supervision (opens in a new tab)

  2. Representation Learning under Limited Supervision

    … by advancing representation learning under limited supervision, focusing on semi-supervised learning, few-shot fine-tuning of foundation models, and adaptation during inference. We propose novel methods to enhance the robustness of semi-supervised learning and few-shot tuning, addressing …

    queens Repository record for Representation Learning under Limited Supervision (opens in a new tab)

  3. Relation Classification with Limited Supervision

    … approaches for relation classification with limited supervision. We start by proposing an approach for learning embeddings for contextual surface patterns, which are the set of surface patterns associated with entity pairs across a text corpus, to provide additional supervision signals for …

    whiterose Download PDF for Relation Classification with Limited Supervision (opens in a new tab)

  4. Recognizing visual communication with limited supervision

    <p>Understanding human communication is the first step towards enabling most human-machine interactions. Deep learning models of today can accurately transcribe and reason across spoken and written forms of human communication. In this work, we focus on the third frontier in human communication --- …

    oxford Repository record for Recognizing visual communication with limited supervision (opens in a new tab)

  5. Learning video representations with limited supervision

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms

    uiuc Repository record for Learning video representations with limited supervision (opens in a new tab)

  6. Guided text summarization with limited supervision

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms

    uiuc Repository record for Guided text summarization with limited supervision (opens in a new tab)

  7. Learning to localize objects with limited supervision

    … object detection architectures for weak supervision. While there are plenty of object detection architectures proposed for supervised object detection, researchers working on weakly supervised detectors use the WSDDN (Weakly Supervised Deep Detection Networks) architecture because it is …

    ets-quebec Download PDF for Learning to localize objects with limited supervision (opens in a new tab)

  8. Towards Generalizable Information Extraction with Limited Supervision

    … addressing information extraction (IE) under limited supervision. In this dissertation, we approach information extraction with limited supervision from three perspectives. Firstly, we refine the previous classification-based extraction paradigm by introducing a query-and-extract framework, …

    vt Repository record for Towards Generalizable Information Extraction with Limited Supervision (opens in a new tab)

  9. Deep learning of visual features with limited supervision.

    … methods for learning deep visual features with limited human supervision, expanding deep learning’s applicability to diverse real-world tasks. We propose solutions in three key areas. First, we introduce a selective pretraining approach that enhances transfer learning by selecting pre-training …

    baylor Repository record for Deep learning of visual features with limited supervision. (opens in a new tab)

  10. Learning Robust Graph Neural Networks with Limited Supervision

    … performance degradation when confronted with limited annotated samples, class imbalance, or noisy graph structures. First, a Dual GNN learning framework is introduced for semi-supervised node classification under limited supervision. The framework comprises two GNN-based node prediction …

    carleton Repository record for Learning Robust Graph Neural Networks with Limited Supervision (opens in a new tab)

  11. Information Extraction on Scientific Literature under Limited Supervision

    … robust techniques capable of functioning with limited supervision. In this thesis, we study the task of information extraction on scientific literature, particularly addressing the challenge of limited (human) supervision. Specifically, our work has delved into four key dimensions of this …

    gatech Repository record for Information Extraction on Scientific Literature under Limited Supervision (opens in a new tab)

  12. Deep learning for computer vision constrained by limited supervision

    … for image classification and re- gression in low supervision settings. The research was conducted on publicly available benchmark image datasets as well as real world data with appli- cations to herbage quality estimation in an agri-tech scope at the VistaMilk SFI centre. Topics include label …

    dcu Download PDF for Deep learning for computer vision constrained by limited supervision (opens in a new tab)

  13. Multi-dimensional mining of unstructured data with limited supervision

    … text data into multi-dimensional knowledge with limited supervision. We investigate two core questions: 1. How to identify task-relevant data with declarative queries in multiple dimensions? 2. How to distill knowledge from data in a multi-dimensional space? To address the above questions, we …

    uiuc Repository record for Multi-dimensional mining of unstructured data with limited supervision (opens in a new tab)

  14. Formality Style Transfer Within and Across Languages with Limited Supervision

    … examples of style transfer are only available in limited quantities. We first address this problem by inducing a lexical formality model based on word embeddings and a small number of representative formal and informal words. This enables us to assign sentential formality scores and rerank …

    maryland Repository record for Formality Style Transfer Within and Across Languages with Limited Supervision (opens in a new tab)

  15. An Adaptive Framework for Classification of Concept Drift with Limited Supervision

    … of the model of the framework in absence of supervision, namely, without using the true classes of the data. The second novelty is a technique that infers the presence of concept drift by measuring the similarity between the decisions of mature classifiers and the decisions of naive …

    whiterose Download PDF for An Adaptive Framework for Classification of Concept Drift with Limited Supervision (opens in a new tab)

  16. Detection and Tracking of Instruments for Robotic Surgery Guidance with Limited Supervision

    … performance on existing segmentation tasks with limited supervision. By redefining surgical instrument segmentation as a unified and part-aware task, this thesis offers a potential foundation for the next generation of artificial intelligence (AI)-driven surgical assistance in the operating room

    kings Repository record for Detection and Tracking of Instruments for Robotic Surgery Guidance with Limited Supervision (opens in a new tab) Download PDF for Detection and Tracking of Instruments for Robotic Surgery Guidance with Limited Supervision (opens in a new tab)

  17. Adaptive Learning for AI Systems: AI Methods for Scientific Domains under Limited Supervision

    … specialization. I first tackle the problem of limited labeled data with novel self-supervised learning approaches. By leveraging spatial relationships in remote sensing data, I demonstrate significant gains in sample efficiency for ecological monitoring. Next, I integrate expert interaction …

    cornell Repository record for Adaptive Learning for AI Systems: AI Methods for Scientific Domains under Limited Supervision (opens in a new tab)

  18. Object Recognition and Visual Question Answering with Limited Supervision: From Episodic Learning to Foundational Models

    … enabling visual understanding under limited supervision has become an important research direction. This thesis studies visual understanding under limited supervision across object recognition and visual question answering (VQA), noting that object recognition answers a fixed question …

    carleton Repository record for Object Recognition and Visual Question Answering with Limited Supervision: From Episodic Learning to Foundational Models (opens in a new tab)

Page 1 of 4