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 30 for “"Zero-shot classification"”.

  1. Vision Language Model Guided Zero-shot Classification

    … tasks in Computer Vision, 2D image and 3D object classification are fundamental tasks which serve as the foundation for numerous applications including scene understanding, robotics and autonomous navigation. Vision Language Model (VLMs) are deep learning architectures designed to process and …

    anu Repository record for Vision Language Model Guided Zero-shot Classification (opens in a new tab)

  2. GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification

    … that redefines optimal transport in the realm of zero-shot classification. Conventional methods often suffer from miscalibration and a lack of adaptability, as they rely on fixed cost matrices derived solely from pre-trained model embeddings. In contrast, GeoTTER addresses these limitations by …

    buffalo Repository record for GeoTTER: Leveraging Local Geometry of Optimal Transport for Zero-Shot Classification (opens in a new tab)

  3. Spatial-Temporal change detection in satellite imaging-monitoring /

    … and the second experiment employs CLIP-based zero-shot classification to effectively detect changes without the need for extensive labeling. Additionally, caption based change classification done which these captions generated using Llama model. The work further investigates the use of the …

    vilnius Repository record for Spatial-Temporal change detection in satellite imaging-monitoring / (opens in a new tab)

  4. Distributional robustness: towards challenging and real-world settings of distribution shift

    … at foundation vision-language models for the zero-shot classification problem, and the challenges of adapting such models from the pre-trained data distribution to a downstream distribution. While vision-language models have gained popularity as a solution for the classification problem, …

    oxford Repository record for Distributional robustness: towards challenging and real-world settings of distribution shift (opens in a new tab)

  5. Generative AI for Digital Pathology: Advancing Diffusion, Vision-Language, and Safety-Aware Models

    … image-caption datasets and the sensitivity of zero-shot classification to prompt design. To address these challenges, language rewrites generated by a large language model (LLM) are used to enrich an existing dataset, resulting in substantial performance gains. Additionally, a novel context …

    cornell Repository record for Generative AI for Digital Pathology: Advancing Diffusion, Vision-Language, and Safety-Aware Models (opens in a new tab)

  6. Multimodal Representation Learning in Medical Using Vision-Language Models

    … extraction and summarization, and modality-aware classification. Using OPEN-PMC-2M, we conduct controlled experiments to quantify the effect of each processing step on contrastive pretraining. Our findings show that subfigure decomposition and enriched captions substantially improve retrieval, …

    york Repository record for Multimodal Representation Learning in Medical Using Vision-Language Models (opens in a new tab)

  7. Optimizing Real-time Traffic Sign Recognition Algorithms For Mobile Devices.

    … systems by focusing on the Detection and Classification modules to accurately recognize a broader range of traffic signs. A novel pipeline leveraging CLIP architecture is proposed, featuring prompt-based classification. An optimized YOLO (You Only Look Once) detection model with an …

    gatech Repository record for Optimizing Real-time Traffic Sign Recognition Algorithms For Mobile Devices. (opens in a new tab)

  8. Hybrid ConVIRT - enhancing medical image-text representation learning of vision language models

    … Mix, and CheXpert) using linear probe and zero-shot classification demonstrates Hybrid-ConVIRT’s enhanced discriminative power and feature robustness, particularly on COVID and CheXpert datasets. Although MedCLIP shows a slight advantage on the Tuberculosis dataset, this is likely due to …

    uoit Repository record for Hybrid ConVIRT - enhancing medical image-text representation learning of vision language models (opens in a new tab)

  9. Enriching vision representation by deep neural networks and self-supervised learning

    … extraction layer. It achieves competitive image classification accuracy with significantly decreased model parameters. Another attempt at efficient deep learning is a proposed channel pruning approach that compresses deep neural networks by identifying and removing redundant channels using …

    njit Repository record for Enriching vision representation by deep neural networks and self-supervised learning (opens in a new tab)

  10. Advancing Generalization in Deep Representation Learning

    … significantly enhances fairness and accuracy in zero-shot classification tasks, surpassing existing debiasing techniques. Together, the methodologies and theoretical insights developed in this thesis substantially advance our understanding and practical approaches to improving generalization at …

    queens Repository record for Advancing Generalization in Deep Representation Learning (opens in a new tab)

  11. Towards Autonomous Histopathological Diagnosis: An End-to-End Multi-Agent AI Framework for Diagnostic Decision-Making and Interpretation

    … that achieves state-of-the-art performance in zero-shot classification and cross-modal retrieval tasks. Building on this foundation, we developed Quilt-Instruct to create Quilt-LLaVA, a large language and vision assistant specifically tailored for histopathology. Quilt-LLaVA can analyze WSI …

    washington Repository record for Towards Autonomous Histopathological Diagnosis: An End-to-End Multi-Agent AI Framework for Diagnostic Decision-Making and Interpretation (opens in a new tab)

  12. Learning to Build Probabilistic Models with Limited Data

    … challenging tasks in this regime including few-shot learning, zero-shot learning, and structured prediction. In the first part of this thesis, we propose a deep metric learning approach to few-shot and zero-shot classification that generalizes from just a few examples. It does so by exploiting a …

    toronto-retro Repository record for Learning to Build Probabilistic Models with Limited Data (opens in a new tab)

  13. Optimizing Large Language Models and Multimodal Approaches for Biomedical Publication and Satellite Imagery

    … include the development of a custom dataset for classification and Question and Answering (Q&A) tasks, fine-tuning Transformer models like the Bidirectional Encoder Representations from Transformers (BERT) and addressing multi-span answer issues with the TAg-based Span Extraction (TASE) model. …

    sdstate Repository record for Optimizing Large Language Models and Multimodal Approaches for Biomedical Publication and Satellite Imagery (opens in a new tab)

  14. Investigating the Impacts of Policy Stringency on the Public Perceptions of Pandemic Policies, Sentiment Analysis of Tweets During the Second and Third COVID-19 Pandemic Waves in Ontario

    … users in Ontario were compiled and sorted using zero-shot classification into subgroups for relevant categories – vaccine mandates, mask policies, and lockdown measures. These tweets were then analyzed using sentiment analysis and the COVID-19 Stringency Index to identify trends in the sentiments …

    waterloo Repository record for Investigating the Impacts of Policy Stringency on the Public Perceptions of Pandemic Policies, Sentiment Analysis of Tweets During the Second and Third COVID-19 Pandemic Waves in Ontario (opens in a new tab)

  15. Identifying Online Conspiracy Theories: A Multiphase Analysis of AI Models

    … Transformer models (BERT, BERTweet); and (3) zero-shot classification with Large Language Models (LLMs). The results reveal a clear hierarchy of performance, with LLMs demonstrating superior accuracy, achieving a top F1-score of 0.880. Notably, a hybrid approach combining Google’s foundation …

    sheffield-hallam Repository record for Identifying Online Conspiracy Theories: A Multiphase Analysis of AI Models (opens in a new tab) Download PDF for Identifying Online Conspiracy Theories: A Multiphase Analysis of AI Models (opens in a new tab) Embargoed until 2027-01-07

  16. Automated Theme Extraction from Homeless Shelter Case Notes: A Comparative Evaluation of Machine Learning and Large Language Model Methods

    … learning baselines, as well as transformer-based zero-shot classification, and prompt engineering and fine-tuning of smaller open-source language models. A manually annotated subset of case notes from the Calgary Drop-In Centre served as the basis for method development and evaluation. Based on …

    calgary Repository record for Automated Theme Extraction from Homeless Shelter Case Notes: A Comparative Evaluation of Machine Learning and Large Language Model Methods (opens in a new tab)

  17. The Comparison of Human and Machine Performance in Object Recognition

    … scenarios without fine-tuning or task-specific zero-shot classification. While fine-tuning can significantly enhance machine performance in constrained tasks, this advantage may overestimate machine capabilities relative to humans. In Chapter 3, I test the assumption that human performance …

    plymouth Repository record for The Comparison of Human and Machine Performance in Object Recognition (opens in a new tab)

  18. ENHANCING NLP CAPABILITIES: STRATEGIES FOR LANGUAGE MODEL ADAPTATION IN LOW-RESOURCE TEXT CLASSIFICATION TASK AND EVALUATIONS

    Nowadays, there are two approaches solving classification tasks in Natural Language Processing (NLP). The traditional way usually includes the adaptation of smaller Pre-trained Large Language Models (BERT, RoBERTa, etc.) to specific downstream tasks that offer both remarkable opportunities and …

    temple Repository record for ENHANCING NLP CAPABILITIES: STRATEGIES FOR LANGUAGE MODEL ADAPTATION IN LOW-RESOURCE TEXT CLASSIFICATION TASK AND EVALUATIONS (opens in a new tab)

  19. Deep Unsupervised Learning for Biodiversity Analyses: Representation learning and clustering of bacterial, mitochondrial, and barcode DNA sequences

    … alignment-free methods in taxonomic classification. Motivated by this success, this dissertation investigates the potential of unsupervised learning-based alignment-free algorithms in genomic signature categorization. We conclude that meaningful information can be learned without …

    waterloo Repository record for Deep Unsupervised Learning for Biodiversity Analyses: Representation learning and clustering of bacterial, mitochondrial, and barcode DNA sequences (opens in a new tab)

  20. Label Shift Problem for Image Classification Tasks -- A Comprehensive Analysis

    … type of distribution shift that happens in classification tasks, where the source domain (train set) and target domain (test set) have different label distributions p(y) but identical distributions of image given label p(x|y). Under label shift, the classifier trained on the source domain …

    anu Repository record for Label Shift Problem for Image Classification Tasks -- A Comprehensive Analysis (opens in a new tab)

Page 1 of 2